Re-enable these in the legacy node, the new one won't have them

.github/ISSUE_TEMPLATE/bug_report.md

@@ -20,7 +20,5 @@ A clear and concise description of what the bug is.
 Information needed to trigger the problem.
 If possible, attach a workflow to reproduce the problem
 
-If a workflow works, but isn't producing the correct output, please enable debug logging with the `PCSetLogLevel` node (from `promptcontrol/tools`) and run your workflow with debug logging enabled, and copy the outputs here.
-
 **Expected behavior**
 A description of what you expected to happen.

.github/workflows/publish.yml

@@ -1,29 +0,0 @@
-name: Publish to Comfy registry
-on:
-  workflow_dispatch:
-  push:
-    branches:
-      - master
-    paths:
-      - "pyproject.toml"
-
-permissions:
-  issues: write
-
-jobs:
-  tests:
-    uses: ./.github/workflows/tests.yml
-  tests_with_comfy:
-    uses: ./.github/workflows/tests_with_comfy.yml
-  publish-node:
-    name: Publish Custom Node to registry
-    runs-on: ubuntu-latest
-    if: ${{ github.repository_owner == 'asagi4' }}
-    needs: [tests, tests_with_comfy]
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v4
-      - name: Publish Custom Node
-        uses: Comfy-Org/publish-node-action@v1
-        with:
-          personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}

.github/workflows/tests.yml

@@ -1,23 +0,0 @@
-name: Run parser tests
-on:
-  - workflow_call
-  - workflow_dispatch
-  - push
-
-jobs:
-  run-parser-tests:
-    name: Run parser tests
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v4
-      - name: Check out ComfyUI
-        uses: actions/checkout@v4
-        with:
-          repository: comfyanonymous/ComfyUI
-          path: ComfyUI
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-      - run: pip install pytest typing-extensions
-      - run: PYTHONPATH=ComfyUI pytest tests/test_parser.py

.github/workflows/tests_with_comfy.yml

@@ -1,40 +0,0 @@
-name: Run tests requiring ComfyUI
-on:
-  workflow_call:
-  workflow_dispatch:
-  push:
-    paths:
-      - prompt_control/adv_encode.py
-      - prompt_control/attention_couple_ppm.py
-      - prompt_control/nodes_lazy.py
-      - prompt_control/prompts.py
-      - prompt_control/parser.py
-      - prompt_control/utils.py
-
-
-jobs:
-  run-graph-tests:
-    name: Run tests requiring ComfyUI
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v4
-      - name: Check out ComfyUI
-        uses: actions/checkout@v4
-        with:
-          repository: comfyanonymous/ComfyUI
-          path: ComfyUI
-      - uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-          cache: pip
-      - name: install-torch
-        run: pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-      - name: install ComfyUI
-        run: pip install pytest typing-extensions -r ComfyUI/requirements.txt
-      - name: Download clip_l.safetensors
-        run: curl -LO https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
-      - name: Force Comfy to use the CPU
-        run: sed -i "s/^cpu_state = CPUState.GPU/cpu_state = CPUState.CPU/g" ComfyUI/comfy/model_management.py
-      - name: Run graph tests
-        run: PYTHONPATH=ComfyUI pytest tests/test_graph.py tests/test_encode.py

.gitignore

@@ -1,2 +1 @@
 __pycache__
-.pyre

Makefile

@@ -1,34 +1,8 @@
-ARGS=
-all: format check test
+all: format check
 	@echo "Done"
-
 check:
-	ty check && ruff check
-
-fix:
-	ruff check --fix
-
+	pyflakes *.py */*.py */*/*.py
 format:
-	ruff format
-
-test:
-	PYTHONPATH=../../ pytest tests/test_parser.py tests/test_cutout.py tests/test_macros.py $(ARGS)
-
-test_graph:
-	PYTHONPATH=../../  pytest tests/test_graph.py $(ARGS)
-
-test_encode:
-	PYTHONPATH=../../  pytest tests/test_encode.py $(ARGS)
-
-test_workflow:
-	PYTHONPATH=../../  pytest tests/test_workflow.py $(ARGS)
-
-test_encode_both:
-	TEST_TE="clip_l t5" PYTHONPATH=../../  pytest tests/test_encode.py $(ARGS)
-
-test_heavy: test_graph test_encode_both
-
-manual_test:
-	PYTHONPATH=../../ python -im prompt_control.manual_test
+	black -l 120 *.py */*.py */*/*.py
 
 .PHONY: check format all

README.md

@@ -1,83 +1,9 @@
-# ComfyUI prompt control
+# ComfyUI prompt control (LEGACY VERSION)
 
-Control LoRA and prompt scheduling, advanced text encoding, regional prompting, and much more, through your text prompt. Prompt Control generates dynamic graphs that are literally identical to handcrafted noodle soup, condensing complicated workflows with dozens of nodes into simple text prompts.
+Go to https://github.com/asagi4/comfyui-prompt-control for the revised version of prompt control.
 
-Prompt Control comes with `PCTextEncode`, which provides advanced text encoding with many additional features compared to ComfyUI's base `CLIPTextEncode`.
-
-A `Basic Text to Image` template is included with the extension, and can be loaded from ComfyUI's template library.
-
-> [!NOTE]
-> v3.0.0 is backwards compatible with existing workflows, but requires at least ComfyUI v0.8.0
-> The parser was rewritten using parsy. It is intended to have the same behaviour as the old parser, but is **significantly** faster.
-> Please report any bugs or incompatibilities you find.
-
-## Notable changes
-
-- `PC: Schedule Prompt` now strips surrounding whitespace by default, which may change some prompts. Add `NOSTRIP()` to your prompt to restore previous behaviour.
-
-## What can it do?
-
-- A1111-style prompt scheduling and filtering without noodle soup.
-- LoRA loading and [scheduling](/doc/schedules.md) using ComfyUI's built-in hook system.
-- Masking, composition and area control ([regional prompting](/doc/regional_prompts.md)) with an implementation of [Attention Couple](/doc/attention_couple.md), also fully schedulable.
-- [Advanced prompt encoding](/doc/basic.md)
-  - Per-encoder prompts for models with multiple text encoders, such as SDXL and Flux.
-  - Prompt combinators like `BREAK`, as well as `CAT`, `AVG()` and `AND` corresponding to ComfyUI's `ConditioningConcat`, `ConditioningAverage` and `ConditioningCombine` nodes.
-  - Different weight interpretation types (ComfyUI, A1111, compel, etc.)
-  - Prompt masking with an implementation of [cutoff](https://github.com/BlenderNeko/ComfyUI_Cutoff).
-- Organize complicated prompts with [segments and prompt macros](/doc/macros.md).
-- [Schedule your own encoder nodes](/doc/node_function.md), allowing prompt control of eg. video or audio models with non-text inputs.
-
-All features are fully schedulable unless otherwise stated. See the [scheduling syntax documentation](doc/schedules.md) to get started.
-
-If you find prompt scheduling inconvenient for some reason, `PCTextEncode` can be used as a drop-in replacement for `CLIPTextEncode` to get everything else.
-
-[This workflow](example_workflows/Workflow%20Comparison.json?raw=1) shows LoRA scheduling and prompt editing and compares it with the same prompt implemented with built-in ComfyUI nodes. You can also find it in the template library.
-
-## Compatibility
-
-Prompt Control uses graph generation,  and tries to delegate functionality to core ComfyUI wherever possible, implementing any hooks and patches in a way that is maximally compatible. This means that it should just work in most cases, even with models and nodes not explicitly supported.
-
-If you encounter issues as a user or if you're a node developer and Prompt Control somehow breaks something, feel free to file a bug report.
-
-## Requirements
-
-The v3 node schema uses features that require at least ComfyUI v0.8.0
-
-If you run into problems, update ComfyUI first.
-
-# Core nodes
-
-**Note**: The documentation refers to the nodes with their internal names for consistency. The display name may change, but ComfyUI's search will always find the nodes with the internal name. `PCLazyTextEncode` and `PCLazyLoraLoader` are the main ones you'll want to use, also known as `PC: Schedule Prompt` and `PC: Schedule LoRas`.
-
-## PCLazyTextEncode and PCLazyTextEncodeAdvanced
-
-`PCLazyTextEncode` uses ComfyUI's lazy graph execution mechanism to generate a graph of `PCTextEncode` and `SetConditioningTimestepRange` nodes from a prompt with schedules. This has the advantage that if a part of the schedule doesn't change, ComfyUI's caching mechanism allows you to avoid re-encoding the non-changed part.
-
-for example, if you first encode `[cat:dog:0.1]` and later change that to `[cat:dog:0.5]`, no re-encoding takes place.
-
-The advanced node enables filtering the prompt for multi-pass workflows.
-
-## PCLazyLoraLoader and PCLazyLoraLoaderAdvanced
-
-This node reads LoRA expressions from the scheduled prompt and constructs a graph of `LoraLoader`s and `CreateHookLora`s as necessary to provide the necessary LoRA scheduling. Just use it in place of a `LoRALoader` and use the output normally.
-
-The Advanced node gives you access to the generated hooks. If you have `apply_hooks` set to true, you **do not** need to apply the `HOOKS`  output to a CLIP model separately; it's provided in case you want to use it elsewhere. The advanced node also enables filtering the prompt for multi-pass workflows.
-
-## PCTextEncode
-
-Encodes a single prompt with advanced (non-scheduling) syntax enabled. This is what actually does most of the work under the hood.
-
-Note: `PCTextEncode` **does not** ignore `<lora:...:1>` and will treat it as part of the prompt. To use a combined prompt for LoRAs and your input, use `PCLazyTextEncode` and `PCLazyLoraLoader`
-
-## PCAddMaskToCLIP
-
-This node attaches masks to a `CLIP` model so that they can be referred to when using the `IMASK` custom mask function of `PCTextEncode`.
-
-## PCSetTextEncodeSettings
-
-This node configures `PCTextEncode` default values for some functions by attaching the information to a `CLIP` model.
+These nodes exist only to reproduce old workflows. They are unmaintained
 
 # Known issues
 
-- Cutoff does not work with models that use non-CLIP text encoders, like Flux. This might be fixable, but it's uncertain if cutoff even makes sense for those models.
+- ComfyUI's LoRA hooks are a bit slower than LoRALoader currently when the LoRA doesn't actually require scheduling. Hopefully this will improve upstream.

__init__.py

@@ -1,45 +1,46 @@
-"""
-@author: asagi4
-@title: ComfyUI Prompt Control
-@nickname: ComfyUI Prompt Control
-@description: Control LoRA and prompt scheduling, advanced text encoding, regional prompting, and much more, through your text prompt. Generates dynamic graphs that are literally identical to handcrafted noodle soup.
-"""
-
-import logging
 import os
 import sys
+import logging
 
-log = logging.getLogger("comfyui-prompt-control")
+from .prompt_control.legacy.node_clip import EditableCLIPEncode, ScheduleToCond
+from .prompt_control.legacy.node_lora import LoRAScheduler, ScheduleToModel, PCSplitSampling, PCWrapGuider
+from .prompt_control.legacy.node_other import (
+    PromptToSchedule,
+    FilterSchedule,
+    PCScheduleSettings,
+    PCScheduleAddMasks,
+    PCApplySettings,
+    PCPromptFromSchedule,
+)
+from .prompt_control.legacy.node_aio import PromptControlSimple
 
-if os.environ.get("PROMPTCONTROL_DEBUG"):
-    log.setLevel(logging.DEBUG)
-else:
-    log.setLevel(logging.INFO)
+NODE_CLASS_MAPPINGS = {}
+NODE_DISPLAY_NAME_MAPPINGS = {}
 
-WEB_DIRECTORY = "web"
+log = logging.getLogger("comfyui-prompt-control-legacy")
+log.propagate = False
+if not log.handlers:
+    h = logging.StreamHandler(sys.stdout)
+    h.setFormatter(logging.Formatter("[%(levelname)s] PromptControl (LEGACY VERSION): %(message)s"))
+    log.addHandler(h)
 
-v1_modules = []
-v3_modules = []
-# Importing things here breaks pytest for whatever reason...
-if "PYTEST_CURRENT_TEST" not in os.environ:
-    import importlib
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy"))
 
-    from comfy_api.latest import ComfyExtension
 
-    if not log.handlers:
-        h = logging.StreamHandler(sys.stdout)
-        h.setFormatter(logging.Formatter("[PromptControl] %(levelname)s: %(message)s"))
-        log.addHandler(h)
-    for node in ["base", "hooks", "tools", "lazy", "anima"]:
-        mod = importlib.import_module(f".prompt_control.nodes_{node}", package=__name__)
-        v3_modules.append(mod)
-
-    class PromptControlExtension(ComfyExtension):
-        async def get_node_list(self):
-            r = []
-            for m in v3_modules:
-                r.extend(m.NODES)
-            return r
-
-    async def comfy_entrypoint():
-        return PromptControlExtension()
+NODE_CLASS_MAPPINGS.update(
+    {
+        "PromptControlSimple": PromptControlSimple,
+        "PromptToSchedule": PromptToSchedule,
+        "PCSplitSampling": PCSplitSampling,
+        "PCPromptFromSchedule": PCPromptFromSchedule,
+        "PCScheduleSettings": PCScheduleSettings,
+        "PCScheduleAddMasks": PCScheduleAddMasks,
+        "PCApplySettings": PCApplySettings,
+        "PCWrapGuider": PCWrapGuider,
+        "FilterSchedule": FilterSchedule,
+        "ScheduleToCond": ScheduleToCond,
+        "ScheduleToModel": ScheduleToModel,
+        "EditableCLIPEncode": EditableCLIPEncode,
+        "LoRAScheduler": LoRAScheduler,
+    }
+)

doc/attention_couple.md

@@ -1,54 +0,0 @@
-# Attention Couple
-
-Attention Couple is an attention-based implementation of regional prompting. it is faster and often more flexible than latent-based masking.
-
-The implementation is based on the one by [pamparamm](https://github.com/pamparamm/ComfyUI-ppm.git), modified to use ComfyUI's hook system. This enables it to work with prompt scheduling.
-
-By default, the implementation produces slightly different results from Pamparamm's implementation because ComfyUI will only run the hook for conds that have it attached and can't batch negative conditionings.
-
-As a consequence of this, however, you can also use `COUPLE` in your negative prompt, and it will work correctly.
-
-To enable batching negative prompts, run your positive and negative prompt through the `PPCAttentionCoupleBatchNegative` node. This will make the outputs identical to pamparamm's implementation and will also improve performance. It will fall back to the default behaviour in cases where batching can't be done, so it should always be safe to use.
-
-## Anima
-
-There is a **very experimental** port of pamparamm's Anima support for Attention Couple in Prompt Control. Because ComfyUI lacks the built-in schedulable hooks required, you must first patch your model with `PC: Anima Attention Couple Model Patch` in addition to using `COUPLE` as usual.
-
-The code was hacked together with minimal thought, so expect bugs and misbehaviour. The port is also currently *not* compatible with NegPIP.
-
-## Syntax
-
-See also the [regional prompting documentation](/doc/regional_prompts.md) for information about `MASK` etc.
-
-### COUPLE: Trigger Attention Couple
-
-You can use `COUPLE` to attach attention-coupled prompts to a base prompt:
-
-For example:
-```
-dog FILL() COUPLE(0.5 1) cat
-```
-
-The full syntax looks as follows (to use `IMASK` you need to attach a custom mask)
-
-`base_prompt COUPLE MASK(0 0.5) coupled prompt 1 with mask COUPLE IMASK(0) coupled prompt 2 with custom mask`
-
-as a shortcut, `COUPLE(maskparams)` is expanded to `COUPLE MASK(maskparams)`, so the above prompt can also be written as:
-
-`base_prompt COUPLE(0 0.5) coupled prompt 1 with mask COUPLE IMASK(0) coupled prompt 2 with custom mask`
-
-Behaviour:
-- If no mask is specified, an implicit `MASK()` is assumed, meaning that the prompt affects the entire image.
-
-- For the base prompt, you can use `FILL()` to automatically mask all parts not masked by other coupled prompts
-
-- If the base prompt has weight set to zero (ie. ´:0` at the end), then the first coupled prompt with non-zero weight becomes the base prompt:
-
-```
-disabled prompt :0 COUPLE new base prompt COUPLE coupled prompt
-```
-
-You can also schedule the weight normally: `prompt :[1:0:0.35]`
-
-> ![NOTE]
-> Note that because the generation still sees and diffuses the full latent, attention coupling is not guaranteed to perfectly limit the effect of your prompt to the masked area.

doc/basic.md

@@ -1,211 +0,0 @@
-# Basic Prompt Syntax
-
-The syntax below documents the features of `PCTextEncode`
-
-## Combining prompts
-
-### AND
-
-`AND` can be used to create "prompt segments". By default, it works as if you had combined the different prompts with `ConditioningCombine`. 
-
-It is also used with regional prompting, see `MASK` and `COUPLE` below.
-
-Prompts can have a weight at the end:
-```
-cat :1 AND dog :2
-```
-`AND` is processed after schedule parsing, so you can change the weight mid-prompt: `cat:[1:2:0.5] AND dog`
-
-The weight defaults to 1. If a prompt's weight is set to 0, it's **skipped entirely.** This can be useful when scheduling to completely disable a prompt:
-
-```
-cat [\:0::0.5] AND dog
-```
-Note that the `:` needs to be escaped with a `\` or it will be interpreted as scheduling syntax.
-
-If `AND` is placed inside quotes (eg. `Text saying "CAT AND DOG"`) it will be treated as regular text.
-
-## Note about processing order
-
-Prompt operators are processed in the following order, meaning that all features "below" another can be affected by the feature above it. That is, `BREAK` can go inside a `TE()` call, but not `AND` or `CAT`.
-
-- DEF macros are expanded
-- Scheduling is expanded, and for each scheduled prompt:
-  - SEGs are processed and the template is expanded
-  - The prompt is split by AND, and for each:
-    - Prompts are split by COUPLE. and for each:
-      - Most functions (like MASK) and cutoffs are evaluated
-      - prompts are split by `AVG()` or CAT
-        - the TE() function is evaluated to set per-encoder prompts
-        - BREAK is evaluated
-        - Everything else
-      - Prompts are combined with `ConditioningAverage` (for `AVG`) or `ConditioningConcat` (for `CAT`)
-    - If coupled prompts exist, the base cond is set up for attention coupling and returned
-  - Prompts split with `AND` are combined with `ConditioningCombine`
-- Each scheduled prompt is restricted to its effective range with  `ConditioningSetTimestepRange`
-
-## Functions
-
-There are some "functions" that can be included in a prompt to affect how it is interpreted.
-
-Functions have the form `FUNCNAME(param1, param2, ...)`. How parameters are interpreted is up to the function. 
-
-In general, function parameters will have default values that are used if the parameter is left empty.
-
-Note: Whitespace is usually *not* stripped from string parameters by default. Commas can be escaped with `\,`
-
-Like `AND`, functions are parsed after regular scheduling syntax has been expanded, allowing things like `[AREA:MASK:0.3](...)`, in case that's somehow useful.
-
-like AND, if any function is placed inside quotes, it will *not* activate and is instead treated as regular text.
-
-### BREAK
-The keyword `BREAK` causes the prompt to be tokenized in separate chunks, padding each chunk to the text encoder's maximum size before encoding.
-
-For some text encoders (like t5), this operation doesn't really make sense and BREAKs are simply ignored.
-
-### CAT
-
-`CAT` encodes each prompt separately before concatenating the resulting tensors into a single conditioning. It behaves identically to ComfyUI's `ConditioningConcat`.
-
-### AVG()
-
-`prompt1 AVG(weight) prompt2` encodes prompt1 and prompt2 separately, and then combines them using `ConditioningAverage`. The default for `weight` is `0.5`.
-
-`AVG` is processed before `BREAK` but after `AND`
-
-`p1 AVG() p2 AVG() p3` combines `p1` and `p2` first, then combines the result with `p3`.
-
-## Prompt weighting (also known as "Advanced CLIP Encode")
-
-### STYLE
-
-Use the syntax `STYLE(weight_interpretation, normalization)` in a prompt to affect how prompts are interpreted.
-
-The weight interpretations available are:
-  - comfy (default)
-  - comfy++
-  - compel
-  - down_weight
-  - A1111
-  - perp
-
-Normalizations are:
-  - none (default)
-  - length
-  - mean
-
-The normalization calculations are independent operations and you can combine them with `+`, eg `STYLE(A1111, length+mean)` or `STYLE(comfy, mean+length)`, or even something silly like `STYLE(perp, mean+length+mean+length)`
-
-The style can be specified separately for each AND:ed prompt, but the first prompt is special; later prompts will "inherit" it as default. For example:
-
-```
-STYLE(A1111) a (red:1.1) cat with (brown:0.9) spots and a long tail AND an (old:0.5) dog AND a (green:1.4) (balloon:1.1)
-```
-will interpret everything as A1111, but
-```
-a (red:1.1) cat with (brown:0.9) spots and a long tail AND STYLE(A1111) an (old:0.5) dog AND a (green:1.4) (balloon:1.1)
-```
-Will interpret the first one using the default ComfyUI behaviour, the second prompt with A1111 and the last prompt with the default again
-
-### SDXL: Configure SDXL prompting parameters
-
-The nodes do not treat SDXL models specially, but there are some utilities that enable SDXL specific functionality.
-
-You can use the function `SDXL(width height, target_width target_height, crop_w crop_h)` to set SDXL prompt parameters. `SDXL()` is equivalent to `SDXL(1024 1024, 1024 1024, 0 0)` unless the default values have been overridden by `PCScheduleSettings`.
-
-### TE: Per-encoder prompts for multi-encoder models
-
-You can specify per-encoder prompts using the `TE` function. The syntax is as follows:
-`TE(encoder_name=prompt)`. Whitespace surrounding the prompt and encoder name are ignored.
-
-For example:
-```
-TE(l=cat) TE(g = (dog:1.1)) TE(t5xxl=tiger)
-```
-The keys to use depend on what key ComfyUI uses for the encoder; for example `l` for CLIP L, `g` for CLIP G, and `t5xxl` for T5 XXL (Flux text encoder).
-
-Use `TE(help)` to print a help text listing available keys.
-
-Things to note:
-- If you set a prompt with `TE`, it will override the prompt outside the function for the specified text encoder.
-- Multiple instances of `TE` are joined with a space. That is, `TE(l=foo)TE(l=bar)` is the same as `TE(l=foo bar)`
-- `AND` and `BREAK` are processed before `TE`, so they do not do anything sensible; `TE(l=foo AND bar)` will parse as two prompts `TE(foo` and `bar)`. `SHIFT`, `SHUFFLE` and `OLDBREAK` do work, however.
-
-### SHUFFLE and SHIFT: Create prompt permutations
-
-Default parameters: `SHUFFLE(seed=0, separator=,, joiner=,)`, `SHIFT(steps=0, separator=,, joiner=,)`
-
-`SHIFT` moves elements to the left by `steps`. The default is 0 so `SHIFT()` does nothing
-`SHUFFLE` generates a random permutation with `seed` as its seed.
-
-These functions are applied to each prompt chunk **after** `BREAK`, `AND` etc. have been parsed. The prompt is split by `separator`, the operation is applied, and it's then joined back by `joiner`.
-
-Multiple instances of these functions are applied in the order they appear in the prompt.
-
-**NOTE** To avoid breaking emphasis syntax, the functions ignore any separators inside parentheses
-
-For example:
-- `SHIFT(1) cat, dog, tiger, mouse` does a shift and results in `dog, tiger, mouse, cat`. (whitespace may vary)
-- `SHIFT(1,;) cat, dog ; tiger, mouse` results in `tiger, mouse, cat, dog`
-- `SHUFFLE() cat, dog, tiger, mouse` results in `cat, dog, mouse, tiger`
-- `SHUFFLE() SHIFT(1) cat, dog, tiger, mouse` results in `dog, mouse, tiger, cat`
-
-- `SHIFT(1) cat,dog BREAK tiger,mouse` results in `dog,cat BREAK tiger,mouse`
-- `SHIFT(1) cat, dog AND SHIFT(1) tiger, mouse` results in `dog, cat BREAK mouse, tiger`
-
-Whitespace is *not* stripped and may also be used as a joiner or separator
-- `SHIFT(1,, ) cat,dog` results in `dog cat`
-
-### NOISE: Add noise to a prompt
-
-The function `NOISE(weight, seed)` adds some random noise into the cond tensor. The seed is optional, and if not specified, the global RNG is used. `weight` should be between 0 and 1.
-
-The usefulness of this is questionable, but it wasn't difficult to implement, so here it is.
-
-## Regional prompting
-
-See [Regional prompting](/doc/regional_prompting.md)
-
-## Cutoff
-
-NOTE: Cutoff syntax might change at some point; it's pretty clunky.
-
-`PCTextEncode` reimplements cutoff from [ComfyUI Cutoff](https://github.com/BlenderNeko/ComfyUI_Cutoff).
-
-The syntax is
-```
-a group of animals, [CUT:white cat:white], [CUT:brown dog:brown:0.5:1.0:1.0:_]
-```
-You should read the prompt as `a group of animals, white cat, brown dog`, but CUT causes the tokens in `target_tokens` to be masked off from the base prompt in `region_text`, so that their effect can be isolated, and you're less likely to get brown cats or white dogs.
-
-Target tokens are treated individually, separated by space, for example, `[CUT:green apple, red apple, green leaf:green apple]` will mask *both* greens and the apple, giving you `+ +, red +, + leaf`. To mask out just `green apple`, use `[CUT:green apple, red apple:green_apple]` which will result in a masked prompt of `+ +, red apple`. Escape `_` with a `\`.
-
-the parameters in the `CUT` section are `region_text:target_tokens:weight;strict_mask:start_from_masked:padding_token` of which only the first two are required. The default values are `weight=1.0`, `strict_mask=1.0` `start_from_masked=1.0`, `padding_token=+`
-
-If `strict_mask`, `start_from_masked` or `padding_token` are specified in more than one CUT, the *last* one becomes the default for any CUTs afterwards that do not explicitly set the parameters. For example, in:
-
-`[CUT:white cat:white:0.5] and [CUT:black parrot, flying:black:1.0:0.5] and [CUT:green apple:green]`
-
-`white cat` will a weight of 0.5, and 1.0 for all parameters, and `black parrot` and `green apple` will *both* have a `strict_mask` parameter of 0.5.
-
-The parameters affect how the masked and unmasked prompts are combined to produce the final embedding. Just play around with them.
-
-## Miscellaneous
-- `<emb:xyz>` is alternative syntax for `embedding:xyz` to work around a syntax conflict with `[embedding:xyz:0.5]` which is parsed as a schedule that switches from `embedding` to `xyz`.
-
-# Experimental features
-
-> [!WARN]
-> These features are may change or disappear without warning
-
-## COUPLE: Attention couple
-
-See [here](/doc/attention_couple.md)
-
-## TE_WEIGHT
-
-For models using multiple text encoders, you can set weights per TE using the syntax `TE_WEIGHT(clipname=weight, clipname2=weight2, ...)` where `clipname` is one of the encoder names printed by `TE(help)`. For example with SDXL, try `TE_WEIGHT(g=0.25, l=0.75)`.
-
-The weights are applied as a multiplier to the TE output. You can also override pooled output multipliers using eg. `l_pooled`.
-
-To set a default value for all encoders, use `TE_WEIGHT(all=weight)`

doc/legacy.md

@@ -0,0 +1,44 @@
+# Legacy node documentation
+
+You really shouldn't be using these anymore
+
+## Old nodes
+The `ScheduleToModel` node patches a model so that when sampling, it'll switch LoRAs between steps. You can apply the LoRA's effect separately to CLIP conditioning and the unet (model).
+
+Swapping LoRAs often can be quite slow without the `--highvram` switch because ComfyUI will shuffle things between the CPU and GPU. When things stay on the GPU, it's quite fast.
+
+If you run out of VRAM during a LoRA swap, the node will attempt to save VRAM by enabling CPU offloading for future generations even in highvram mode. This persists until ComfyUI is restarted.
+
+You can also set the `PC_RETRY_ON_OOM` environment variable to any non-empty value to automatically retry sampling once if VRAM runs out.
+
+## ScheduleToCond (deprecated)
+Produces a combined conditioning for the appropriate timesteps. From a schedule. Also applies LoRAs to the CLIP model according to the schedule.
+
+## ScheduleToModel (deprecated)
+Produces a model that'll cause the sampler to reapply LoRAs at specific steps according to the schedule.
+
+This depends on a callback handled by a monkeypatch of the ComfyUI sampler function, so it might not work with custom samplers, but it shouldn't interfere with them either.
+
+## PCSplitSampling (deprecated)
+Causes sampling to be split into multiple sampler calls instead of relying on timesteps for scheduling. This makes the schedules more accurate, but seems to cause weird behaviour with SDE samplers. (Upstream bug?)
+
+
+## PromptControlSimple (deprecated)
+This node exists purely for convenience. It's a combination of `PromptToSchedule`, `ScheduleToCond`, `ScheduleToModel` and `FilterSchedule` such that it provides as output a model, positive conds and negative conds, both with and without any specified filters applied.
+
+This makes it handy for quick one- or two-pass workflows.
+
+## Older nodes
+
+- `EditableCLIPEncode`: A combination of `PromptToSchedule` and `ScheduleToCond`
+- `LoRAScheduler`: A combination of `PromptToSchedule`, `FilterSchedule` and `ScheduleToModel`
+
+# Known issues
+
+- If you use LoRA scheduling in a workflow with `LoRALoader` nodes, you might get inconsistent results. For now, just avoid mixing `ScheduleToModel` or `LoRAScheduler` with `LoRALoader`. See https://github.com/asagi4/comfyui-prompt-control/issues/36
+- Workflows using `SamplerCustom` will calculate LoRA schedules based on the number of sigmas given to the sampler instead of the number of steps, since that information isn't available.
+- `CUT` does not work with `STYLE:perp`
+- `PCSplitSampling` overrides ComfyUI's `BrownianTreeNoiseSampler` noise sampling behaviour so that each split segment doesn't add crazy amounts of noise to the result with some samplers.
+- Split sampling may have weird behaviour if your step percentages go below 1 step.
+- Interpolation is probably buggy and will likely change behaviour whenever code gets refactored.
+- If execution is interrupted and LoRA scheduling is used, your models might be left in an undefined state until you restart ComfyUI

doc/macros.md

@@ -1,99 +0,0 @@
-## DEF: Lightweight prompt macros
-
-You can define "prompt macros" by using `DEF`.  Macros are expanded before any other parsing takes place. The expansion continues until no further changes occur. Recursion will raise an error.
-
-`PCLazyTextEncode` and `PCLazyLoraLoader` expand macros, but `PCTextEncode` **does not**. If you need to expand macros for a single prompt, use `PCMacroExpand`
-
-```
-DEF(MYMACRO=this is a prompt)
-[(MYMACRO:0.6):(MYMACRO:1.1):0.5]
-```
-is equivalent to
-```
-[(this is a prompt:0.5):(this is a prompt:1.1):0.5]
-```
-### Macro parameters
-It's also possible to give parameters to a macro:
-```
-DEF(MYMACRO=[(prompt $1:$2):(prompt $1:$3):$4])
-MYMACRO(test; 1.1; 0.7; 0.2)
-```
-gives
-```
-[(prompt test:1.1):(prompt test:0.7):0.2]
-```
-in this form, the variables $N (where N is any number corresponding to a positional parameter) will be replaced with the given parameter. The parameters must be separated with a semicolon, and can be empty.
-
-You can also optionally specify default values:
-
-```
-DEF(MACRO(example; 0; 1)=[$1:$2,$3])
-MACRO MACRO(test; 0.2)
-```
-gives
-```
-[example:0,1] [test:0.2,1]
-```
-
-```
-DEF(MACRO() = [a:$1:0.5])
-```
-sets the default value of `$1` to an empty string.
-
-### Unspecified parameters in macros
-
-Unspecified parameters (either via defaults or explicitly given) will not be substituted. Compare:
-
-```
-DEF(mything=a "$1" b "$2")
-mything
-mything()
-mything(A)
-```
-
-gives
-
-```
-a "$1" b "$2"
-a "" b "$2"
-a "A" b "$2"
-```
-
-## SEG: Split your prompt into named segments
-
-Syntax: `SEG(segment_name)`
-
-To help with organizing prompts, you can use the `SEG` function. For example:
-```
-This is a comic
-Top panel: $CAT. $SEG3
-Bottom panel: $DOG
-
-SEG(DOG)
-A dog chasing its
-  tail in a living room.
-SEG(CAT)
-
-a sleeping cat
-
-SEG
-The cat has orange fur with white stripes
-```
-This produces:
-```
-This is a comic
-Top panel: a sleeping cat. The cat has orange fur with white stripes
-Bottom panel: A dog chasing its
-  tail in a living room.
-```
-
-> [!NOTE]
-> Unlike macros, SEGs are processed *after* scheduling syntax has been expanded, except in the LoRA loader (this may change later, but requires a bit of refactoring)
-
-In this case, the first section before any `SEG` becomes the *template* and any text after a `SEG` call becomes part of that segment. Whitespace is stripped from the start and end of segments and the template.
-
-In the template, you can refer to segments by either their index (starting from 1) or the given name, prefixed with a `$SEG`, so in this example, `$SEG1` is the same as `$PANEL1`
-
-Segments can also refer to each other. Recursion will terminate, but produces weird outputs.
-
-Naming segments is optional, in which case you will have to refer to it by its index.

doc/node_function.md

@@ -1,41 +0,0 @@
-# The NODE function
-
-The `NODE` function allows you to use any other text encoding node within `PC: Schedule Prompt`, replacing the default `PCTextEncode` and allowing for example video model scheduling.
-
-> [!NOTE]
-> When using NODE, you lose access to *all* special syntax provided by `PCTextEncode`. Only SEGs, macros and scheduling will continue to work since those are processed at graph expansion time before the text prompt is passed into the node.
-
-## Basic usage
-
-Use `NODE(NodeClassName, textinputname)` in a prompt to generate a graph using any node that's compatible. The requirements are as follows:
-- The node must have a CLIP parameter (which must be named `clip`)
-- It must have a text field
-- It must return a `CONDITIONING` as its first return value.
-
-For example, if you for some reason do not want the advanced features of `PCTextEncode`, use `NODE(CLIPTextEncode)` in the prompt and you'll still get scheduling with ComfyUI's regular TE node.
-
-The default parameters are `PCTextEncode` and `text`.
-
-## Advanced Usage with arbitrary parameters
-
-Advanced usage of `NODE` can be complicated. For an example, see [The H3 workflow](/example_workflows/Prompt%20Control%20with%20MiniMax%20H3.json?raw=1). You can also find it in the template library.
-
-The full synopsis of the function is `NODE(NodeClassName, textinputname, arg_spec)` where `arg_spec` is a semicolon-separated list of `parameter_name json_value` pairs. In raw form, it looks like this:
-```
-NODE(MiniMaxH3ImageToVideo, prompt, vae ["1", 0]; width 1024; height 1024; first_frame ["2", 0])
-```
-
-The names and inputs must match the ComfyUI API format which **may differ from frontend names**. You can export your workflow in API format and inspect it to see how inputs are passed in to nodes.
-
-The arrays are literal ComfyUI node links, meaning the `vae` parameter is taken from node ID "1" first output and `first_frame` from node ID "2" first output.
-
-The values are arbitrary JSON literals, meaning that you can also pass in constant values. To pass in literal strings for example, you need to use quotes `"like this"`.
-
-This is intended to be used with the helper node `PC: NODE Input Helper`, which can be used to pass arbitrary parameters (named `$a` to `$n`) to the encoder. The recommended pattern is to put something like the following:
-```
-SEG(node)
-NODE(MiniMaxH3ImageToVideo, prompt, vae $a; width $b; height $c; length $d; first_frame $e)
-```
-to the helper and then concatenate it at the end of your prompt (use whitespace as a separator). You can then trigger the node with `$node` in your prompt. (see [documentation](/doc/macros.md) for `SEG`)
-
-The helper will replace the parameters with the correct ComfyUI link values.

doc/regional_prompts.md

@@ -1,63 +0,0 @@
-# Regional prompting
-
-This section documents the masking functionality of `PCTextEncode`
-
-See also [Attention Couple](/doc/attention_couple.md)
-
-Remember that when using the lazy nodes, prompt scheduling applies to masks as well, so you can change or enable/disable regional prompts at any point during sampling.
-
-## Behaviour
-
-For each prompt separated by `AND`, you can specify either latent masks or an area.
-
-- When masked, ComfyUI generates the model output using the **full latent** as the input, and then applies the mask to the output before adding it to your latent for the next step.
-- When an area is specified, ComfyUI generates a separate model output using the **part of the latent specified by the area** and then composites it into the full latent afterwards.
-- You can have *both* an AREA and a MASK specified, in which case the mask is applied to the latent specified by the AREA.
-
-For example, consider a 1024 by 1024 (width x height) generation:
-
-- `cat MASK(0 0.5, 0 1) AND dog MASK(0.5 1, 0 1)` generates two outputs at 1024x1024 for "dog" and "cat", then masks half of them off and adds the results together. The following step still see both the dog and the cat from the previous step, so they may blend slightly.
-
-- `cat AREA(0 0.5, 0 1) AND dog AREA(0.5 1, 0 1)` generates two completely separate outputs at **512**x1024 and then composites them together into the 1024x1024 latent. Because the areas do not overlap, the generation for `cat` will not see the output of `dog` and vice versa in subsequent steps as long as the area restriction is in effect.
-
-## MASK, IMASK and AREA
-
-You can use `MASK(x1 x2, y1 y2, weight, op)` to specify a region mask for a prompt. The values are specified as a percentage with a float between `0` and `1`, or as absolute pixel values (these can't be mixed). `1` will be interpreted as a percentage instead of a pixel value.
-
-Multiple `MASK` or `IMASK` calls will be composited together using ComfyUI's `MaskComposite` node, using `op` as the `operation` parameter (defaulting to `multiply`).
-
-Similarly, you can use `AREA(x1 x2, y1 y2, weight)` to specify an area for the prompt (see ComfyUI's area composition examples). The area is calculated by ComfyUI relative to your latent size.
-
-### Custom masks: IMASK and `PCAddMaskToCLIP`
-
-You can attach custom masks to a `CLIP` with the `PC: Attach Mask` nodes and then refer to those masks in the prompt using `IMASK(index, weight, op)`. Indexing starts from zero, so 0 is the first attached mask etc. `PCSCheduleAddMasks` ignores empty inputs, so if you only add a mask to the `mask4` input, it will still have index 0.
-
-Applying the nodes multiple times *appends* masks rather than overriding existing ones, so if you need more than 4, you can just use it more than once.
-
-### Behaviour of multiple masks
-If multiple `MASK`s are specified, they are combined together with ComfyUI's `MaskComposite` node, with `op` specifying the operation to use (default `multiply`). In this case, the combined mask weight can be set with `MASKW(weight)` (defaults to 1.0).
-
-Masks assume a size of `(512, 512)`, unless overridden with `PC: Configure PCTextEncode` and pixel values will be relative to that. ComfyUI will scale the mask to match the image resolution. You can change it manually by using `MASK_SIZE(width, height)` anywhere in the prompt,
-
-These are handled per `AND`-ed prompt, so in `prompt1 AND MASK(...) prompt2`, the mask will only affect prompt2.
-
-The default values are `MASK(0 1, 0 1, 1)` and you can omit unnecessary ones, that is, `MASK(0 0.5, 0.3)` is `MASK(0 0.5, 0.3 1, 1)`
-
-Note that because the default values are percentages, `MASK(0 256, 64 512)` is valid, but `MASK(0 200)` will raise an error.
-
-Masking does not affect LoRA scheduling unless you set unet weights to 0 for a LoRA.
-
-## FEATHER: Mask operations
-
-When you use `MASK` or `IMASK`, you can also call `FEATHER(left top right bottom)` to apply feathering using ComfyUI's `FeatherMask` node. The values are in pixels and default to `0`.
-
-If multiple masks are used, `FEATHER` is applied *before compositing* in the order they appear in the prompt, and any leftovers are applied to the combined mask. If you want to skip feathering a mask while compositing, just use `FEATHER()` with no arguments.
-
-For example:
-```
-MASK(1) MASK(2) MASK(3) FEATHER(1) FEATHER() FEATHER(3) weirdmask FEATHER(4)
-```
-
-gives you a mask that is a combination of 1, 2 and 3, where 1 and 3 are feathered before compositing and then `FEATHER(4)` is applied to the composite.
-
-The order of the `FEATHER` and `MASK` calls doesn't matter; you can have `FEATHER` before `MASK` or even interleave them.

doc/schedules.md

@@ -1,120 +0,0 @@
-# Prompt Schedule Syntax
-
-> [!TIP]
-> If you're viewing this on GitHub, I recommend opening the outline by clicking the button in the top right corner of the text view (it is annoyingly easy to miss).
-
-> [!NOTE]
-> The syntax documented in this section is only available with the `PC: Schedule Prompt` and `PC: Schedule LoRAs` nodes and their advanced variants.
-
-Scheduling syntax is available with is similar to A1111, but only fractions are supported for steps. LoRAs are scheduled by including them in a scheduling expression.
-
-Besides the syntax documented below, the [basic syntax](/doc/basic.md) and [prompt macro](/doc/macros.md) features are also automatically available.
-
-```
-a [large::0.1] [cat|dog:0.05] [<lora:somelora:0.5:0.6>::0.5]
-[in a park:in space:0.4]
-```
-## Note on whitespace
-`PC: Schedule Prompt` will strip leading and following whitespace from the prompt automatically. If you really want whitespace in your prompt, include `NOSTRIP()` in your prompt.
-
-## Comments and escaping
-
-In schedules, any text on a line following a `#` is considered a comment and removed, including the `#` character.
-You can escape the following characters in places where they would otherwise conflict with syntax:
-
-- `#` with `\#`
-- `:` with `\:`
-- `\` with `\\`
-
-Escaping is only required if it would otherwise be considered syntax, that is `\o/` will be interpreted literally and the `\` does not need to be escaped, but in `[embedding:a:0.5]` you would need to escape the `:`.
-
-## Scheduled prompts
-
-There are two forms of scheduled prompts.
-
-### Basic scheduling expressions
-Basic expressions take the form `[before:after:X]` where `X` is the switch point, a decimal number between 0.0 and 1.0 inclusive, representing 0 to 100% of timesteps. Either prompt can also be empty.
-For example:
-```
-a [red:blue:0.5] cat
-```
-switches from `a red cat` to `a blue cat` at 0.5. `before` and `after` can be arbitrary prompts (`after` can also be empty), including other scheduling expressions, allowing nesting:
-```
-a [red:[blue::0.7]:0.5] cat
-```
-
-switches from `a red cat` to `a blue cat` at 0.5 and to `a cat` at 0.7
-
-For convenience `[cat:0.5]` is equivalent to `[:cat:0.5]` meaning it switches from empty to `cat` at 0.5.
-
-### Range expressions
-
-The most general form of a schedule is a range expression: For example, in `prompt [before:during:after:0.3,0.7]`, The prompt be `prompt before` until 0.3, `prompt during` until 0.7, and then `prompt after`. This form is equivalent to `prompt [before:[during:after:0.7]:0.3]`
-
-For convenience, `[during:0.1,0.4]` is equivalent to `[:during::0.1,0.4]` and `[during:after:0.1,0.4]` is equivalent to `[:during:after:0.1,0.4]`.
-
-`[before:during:after:0.1]` is the same as `[before:during:after:0.1,1.0]` which is same as `[before:during:0.1]`
-
-
-### Using step numbers with the Advanced nodes
-
-If you provide a non-zero value to `num_steps` to the `Advanced` versions of the scheduling nodes, you will be able to use step numbers in prompts.
-
-For now, a value between 0 and 1.0 will be interpreted as a percentage if it contains a ., and as an absolute step otherwise.
-
-This is just syntactic sugar. Behind the scenes, the values are converted to percentages and have normal ComfyUI scheduling behaviour.
-
-## Tag selection
-Using the `FilterSchedule` node, in addition to step percentages, you can use a *tag* to select part of an input:
-```
-a large [dog:cat<lora:catlora:0.5>:SECOND_PASS]
-```
-Set the `tags` parameter in the `FilterSchedule` node to filter the prompt. If the tag matches any tag `tags` (comma-separated), the second option is returned (`cat`, in this case, with the LoRA). Otherwise, the first option is chosen (`dog`, without LoRA).
-
-the values in `tags` are case-insensitive, but the tags in the input **must** be uppercase A-Z and underscores only, or they won't be recognized. That is, `[dog:cat:hr]` will not work.
-
-For example, a prompt
-```
-a [black:blue:X] [cat:dog:Y] [walking:running:Z] in space
-```
-with `tags` `x,z` would result in the prompt `a blue cat running in space`
-
-The three prompt form `[a:b:c:TAG]` is parsed, but ignores `b` and is equivalent to `[a:c:TAG]`.
-
-## LoRA Scheduling
-When using the lazy graph building nodes, LoRAs can be scheduled by referring to them in a scheduling expression, like so:
-
-`<lora:fulllora:1> [<lora:partialora:1>::0.5]`
-
-This will schedule `fulllora` for the entire duration of the prompt and `partiallora` until half of sampling is complete.
-
-You can refer to LoRAs by using the filename without extension and subdirectories will also be searched. For example, `<lora:cats:1>`. will match both `cats.safetensors` and `sd15/animals/cats.safetensors`. If there are multiple LoRAs with the same name, the first match will be loaded.
-
-Alternatively, the name can include the full directory path relative to ComfyUI's search paths, without extension: `<lora:XL/sdxllora:0.5>`. In this case, the *full* path must match.
-
-You can also give the exact path (including the extension) as shown in `LoRALoader`.
-
-If no match is found, the node will try to replace spaces with underscores and search again. That is, `<lora:cats and dogs:1>` will find `cats_and_dogs.safetensors`. This helps with some autocompletion scripts that replace underscores with spaces.
-
-Finally, if none of the above produce a match, the search term will be split by whitespace and files that contain all of the parts in any order will be considered. If this returns only a single match, it will be loaded. For example, consider LoRAs:
-
-- `xl/red_cats.safetensors`
-- `flux/blue_cats.safetensors`
-- `flux/red_cats.safetensors`
-
-Then `<lora:cats xl:1>` would match the red cats LoRA, but `cats flux` would be ambiguous and not match.
-
-## Alternating
-
-Alternating syntax is `[a|b:pct_steps]`, causing the prompt to alternate every `pct_steps`. `pct_steps` defaults to 0.1 if not specified. You can also have more than two options.
-
-
-## Sequences
-
-The syntax `[SEQ:a:N1:b:N2:c:N3]` is shorthand for `[a:[b:[c::N3]:N2]:N1]` ie. it switches from `a` to `b` to `c` to nothing at the specified points in sequence.
-
-Might be useful with Jinja templating (see https://github.com/asagi4/comfyui-utility-nodes). For example:
-```
-[SEQ<% for x in steps(0.1, 0.9, 0.1) %>:<lora:test:<= sin(x*pi) + 0.1 =>>:<= x =><% endfor %>]
-```
-generates a LoRA schedule based on a sinewave

doc/syntax.md

@@ -0,0 +1,205 @@
+# Scheduling syntax
+
+Syntax is like A1111 for now, but only fractions are supported for steps. LoRAs are scheduled by including them in a scheduling expression.
+
+```
+a [large::0.1] [cat|dog:0.05] [<lora:somelora:0.5:0.6>::0.5]
+[in a park:in space:0.4]
+```
+
+## Scheduled prompts
+
+There are two forms of scheduled prompts.
+
+### Basic scheduling expressions
+Basic expressions take the form `[before:after:X]` where `X` is the switch point, a decimal number between 0.0 and 1.0 inclusive, representing 0 to 100% of timesteps.
+For example:
+```
+a [red:blue:0.5] cat
+```
+switches from `a red cat` to `a blue cat` at 0.5. `before` and `after` can be arbitrary prompts (`after` can also be empty), including other scheduling expressions, allowing nesting:
+```
+a [red:[blue::0.7]:0.5] cat
+```
+
+switches from `a red cat` to `a blue cat` at 0.5 and to `a cat` at 0.7
+
+
+**Note:** As a special case, `[cat:0.5]` is like `[:cat:0.5]` meaning it switches from empty to `cat` at 0.5. Currently, `[:cat:0.5]` doesn't actually parse correctly, so you **must** use the shortcut form
+
+### Range expressions
+
+You can also use `a [during:after:0.3,0.7]` as a shortcut. The prompt be `a` until 0.3, `a during` until 0.7, and then `a after`. This form is equivalent to `[[during:after:0.7]:0.3]`
+For convenience, `[during:0.1,0.4]` is equivalent to `[during::0.1,0.4]`
+
+## Tag selection
+Using the `FilterSchedule` node, in addition to step percentages, you can use a *tag* to select part of an input:
+```
+a large [dog:cat<lora:catlora:0.5>:SECOND_PASS]
+```
+Set the `tags` parameter in the `FilterSchedule` node to filter the prompt. If the tag matches any tag `tags` (comma-separated), the second option is returned (`cat`, in this case, with the LoRA). Otherwise, the first option is chosen (`dog`, without LoRA).
+
+the values in `tags` are case-insensitive, but the tags in the input **must** be uppercase A-Z and underscores only, or they won't be recognized. That is, `[dog:cat:hr]` will not work.
+
+For example, a prompt
+```
+a [black:blue:X] [cat:dog:Y] [walking:running:Z] in space
+```
+with `tags` `x,z` would result in the prompt `a blue cat running in space`
+
+
+## LoRA Scheduling
+LoRAs can be scheduled by referring to them in a scheduling expression, like so:
+
+`<lora:fulllora:1> [<lora:partialora:1>::0.5]`
+
+This will schedule `fulllora` for the entire duration of the prompt and `partiallora` until half of sampling is complete.
+
+`PCLoraHooksFromSchedule` creates a properly scheduled `HOOKS` object from LoRA expressions included in the prompt. The older (deprecated) `ScheduleToModel` nodes will monkeypatch ComfyUI sampling and attempt to perform LoRA loading directly.
+
+You can refer to LoRAs by using the filename without extension and subdirectories will also be searched. For example, `<lora:cats:1>`. will match both `cats.safetensors` and `sd15/animals/cats.safetensors`. If there are multiple LoRAs with the same name, the first match will be loaded.
+
+Alternatively, the name can include the full directory path relative to ComfyUI's search paths, without extension: `<lora:XL/sdxllora:0.5>`. In this case, the *full* path must match.
+
+If no match is found, the node will try to replace spaces with underscores and search again. That is, `<lora:cats and dogs:1>` will find `cats_and_dogs.safetensors`. This helps with some autocompletion scripts that replace underscores with spaces.
+
+Finally, you can give the exact path (including the extension) as shown in `LoRALoader`.
+
+
+## Alternating
+
+Alternating syntax is `[a|b:pct_steps]`, causing the prompt to alternate every `pct_steps`. `pct_steps` defaults to 0.1 if not specified. You can also have more than two options.
+
+
+## Sequences
+
+The syntax `[SEQ:a:N1:b:N2:c:N3]` is shorthand for `[a:[b:[c::N3]:N2]:N1]` ie. it switches from `a` to `b` to `c` to nothing at the specified points in sequence.
+
+Might be useful with Jinja templating (see https://github.com/asagi4/comfyui-utility-nodes). For example:
+```
+[SEQ<% for x in steps(0.1, 0.9, 0.1) %>:<lora:test:<= sin(x*pi) + 0.1 =>>:<= x =><% endfor %>]
+```
+generates a LoRA schedule based on a sinewave
+
+## Prompt interpolation
+
+Note: Not currently supported by `PCEncodeSchedule`
+
+`a red [INT:dog:cat:0.2,0.8:0.05]` will attempt to interpolate the tensors for `a red dog` and `a red cat` between the specified range in as many steps of 0.05 as will fit.
+
+
+# Basic prompt syntax
+
+This syntax is also available in outside scheduled prompts, where applicable.
+
+## LoRA loading
+
+The A111-style syntax `<lora:loraname:weight>` can be used to load LoRAs via the prompt. See LoRA scheduling above.
+
+## Combining prompts, A1111-style
+
+- The keyword `BREAK` causes the prompt to be tokenized in separate chunks, which results in each chunk being individually padded to the text encoder's maximum token length. This is mostly equivalent to the `ConditioningConcat` node.
+
+`AND` can be used to combine prompts. You can also use a weight at the end. It does a weighted sum of each prompt,
+```
+cat :1 AND dog :2
+```
+The weight defaults to 1 and are normalized so that `a:2 AND b:2` is equal to `a AND b`. `AND` is processed after schedule parsing, so you can change the weight mid-prompt: `cat:[1:2:0.5] AND dog`
+
+
+## Functions
+
+There are some "functions" that can be included in a prompt to do various things. 
+
+Functions have the form `FUNCNAME(param1, param2, ...)`. How parameters are interpreted is up to the function.
+Note: Whitespace is *not* stripped from string parameters by default. Commas can be escaped with `\,`
+
+Like `AND`, these functions are parsed after regular scheduling syntax has been expanded, allowing things like `[AREA:MASK:0.3](...)`, in case that's somehow useful.
+
+### SDXL
+
+The nodes do not treat SDXL models specially, but there are some utilities that enable SDXL specific functionality.
+
+You can use the function `SDXL(width height, target_width target_height, crop_w crop_h)` to set SDXL prompt parameters. `SDXL()` is equivalent to `SDXL(1024 1024, 1024 1024, 0 0)` unless the default values have been overridden by `PCScheduleSettings`.
+
+To set the `clip_l` prompt, as with `CLIPTextEncodeSDXL`, use the function `CLIP_L(prompt text goes here)`.
+
+Things to note:
+- Multiple instances of `CLIP_L` are joined with a space. That is, `CLIP_L(foo)CLIP_L(bar)` is the same as `CLIP_L(foo bar)`
+- Using `BREAK` isn't supported in it; it'll just parse as the plain word BREAK.
+- similarly, `AND` inside `CLIP_L` does not do anything sensible; `CLIP_L(foo AND bar)` will parse as two prompts `CLIP_L(foo` and `bar)`
+- `CLIP_L` and `SDXL` have no effect on SD 1.5.
+- The rest of the prompt becomes the `clip_g` prompt.
+- If there is no `CLIP_L` or `SDXL`, the prompts will work as with `CLIPTextEncode`.
+
+### SHUFFLE and SHIFT
+
+Default parameters: `SHUFFLE(seed=0, separator=,, joiner=,)`, `SHIFT(steps=0, separator=,, joiner=,)`
+
+`SHIFT` moves elements to the left by `steps`. The default is 0 so `SHIFT()` does nothing
+`SHUFFLE` generates a random permutation with `seed` as its seed.
+
+These functions are applied to each prompt chunk **after** `BREAK`, `AND` etc. have been parsed. The prompt is split by `separator`, the operation is applied, and it's then joined back by `joiner`.
+
+Multiple instances of these functions are applied in the order they appear in the prompt.
+
+**NOTE:** These functions are *not* smart about syntax and will break emphasis if the separator occurs inside parentheses. I might fix this at some point, but for now, keep this in mind.
+
+For example:
+- `SHIFT(1) cat, dog, tiger, mouse` does a shift and results in `dog, tiger, mouse, cat`. (whitespace may vary)
+- `SHIFT(1,;) cat, dog ; tiger, mouse` results in `tiger, mouse, cat, dog`
+- `SHUFFLE() cat, dog, tiger, mouse` results in `cat, dog, mouse, tiger`
+- `SHUFFLE() SHIFT(1) cat, dog, tiger, mouse` results in `dog, mouse, tiger, cat`
+
+- `SHIFT(1) cat,dog BREAK tiger,mouse` results in `dog,cat BREAK tiger,mouse`
+- `SHIFT(1) cat, dog AND SHIFT(1) tiger, mouse` results in `dog, cat BREAK mouse, tiger`
+
+Whitespace is *not* stripped and may also be used as a joiner or separator
+- `SHIFT(1,, ) cat,dog` results in `dog cat`
+
+### NOISE
+
+The function `NOISE(weight, seed)` adds some random noise into the prompt. The seed is optional, and if not specified, the global RNG is used. `weight` should be between 0 and 1.
+
+### MASK, IMASK and AREA
+
+You can use `MASK(x1 x2, y1 y2, weight, op)` to specify a region mask for a prompt. The values are specified as a percentage with a float between `0` and `1`, or as absolute pixel values (these can't be mixed). `1` will be interpreted as a percentage instead of a pixel value.
+
+Similarly, you can use `AREA(x1 x2, y1 y2, weight)` to specify an area for the prompt (see ComfyUI's area composition examples). The area is calculated by ComfyUI relative to your latent size.
+
+#### Custom masks: IMASK and `PCScheduleAddMasks`
+
+You can attach custom masks to a `PROMPT_SCHEDULE` with the `PCScheduleAddMasks` node and then refer to those masks in the prompt using `IMASK(index, weight, op)`. Indexing starts from zero, so 0 is the first attached mask etc. `PCSCheduleAddMasks` ignores empty inputs, so if you only add a mask to the `mask4` input, it will still have index 0.
+
+Applying `PCScheduleAddMasks` multiple times *appends* masks to a schedule rather than overriding existing ones, so if you need more than 4, you can just use it more than once.
+
+#### Behaviour of masks
+If multiple `MASK`s are specified, they are combined together with ComfyUI's `MaskComposite` node, with `op` specifying the operation to use (default `multiply`). In this case, the combined mask weight can be set with `MASKW(weight)` (defaults to 1.0).
+
+Masks assume a size of `(512, 512)`, unless overridden with `PCScheduleSettings` and pixel values will be relative to that. ComfyUI will scale the mask to match the image resolution. You can change it manually by using `MASK_SIZE(width, height)` anywhere in the prompt,
+
+These are handled per `AND`-ed prompt, so in `prompt1 AND MASK(...) prompt2`, the mask will only affect prompt2.
+
+The default values are `MASK(0 1, 0 1, 1)` and you can omit unnecessary ones, that is, `MASK(0 0.5, 0.3)` is `MASK(0 0.5, 0.3 1, 1)`
+
+Note that because the default values are percentages, `MASK(0 256, 64 512)` is valid, but `MASK(0 200)` will raise an error.
+
+Masking does not affect LoRA scheduling unless you set unet weights to 0 for a LoRA.
+
+### FEATHER
+
+When you use `MASK` or `IMASK`, you can also call `FEATHER(left top right bottom)` to apply feathering using ComfyUI's `FeatherMask` node. The values are in pixels and default to `0`.
+
+If multiple masks are used, `FEATHER` is applied *before compositing* in the order they appear in the prompt, and any leftovers are applied to the combined mask. If you want to skip feathering a mask while compositing, just use `FEATHER()` with no arguments.
+
+For example:
+```
+MASK(1) MASK(2) MASK(3) FEATHER(1) FEATHER() FEATHER(3) weirdmask FEATHER(4)
+```
+
+gives you a mask that is a combination of 1, 2 and 3, where 1 and 3 are feathered before compositing and then `FEATHER(4)` is applied to the composite.
+
+The order of the `FEATHER` and `MASK` calls doesn't matter; you can have `FEATHER` before `MASK` or even interleave them.
+
+## Miscellaneous
+- `<emb:xyz>` is alternative syntax for `embedding:xyz` to work around a syntax conflict with `[embedding:xyz:0.5]` which is parsed as a schedule that switches from `embedding` to `xyz`.

example_workflows/Basic Text to Image.json

@@ -1,672 +0,0 @@
-{
-  "id": "e820c2fb-9502-45b7-a864-684757dddcdf",
-  "revision": 0,
-  "last_node_id": 18,
-  "last_link_id": 20,
-  "nodes": [
-    {
-      "id": 1,
-      "type": "CheckpointLoaderSimple",
-      "pos": [
-        -135,
-        -930
-      ],
-      "size": [
-        315,
-        98
-      ],
-      "flags": {},
-      "order": 0,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [
-        {
-          "name": "MODEL",
-          "type": "MODEL",
-          "slot_index": 0,
-          "links": [
-            2
-          ]
-        },
-        {
-          "name": "CLIP",
-          "type": "CLIP",
-          "slot_index": 1,
-          "links": [
-            3
-          ]
-        },
-        {
-          "name": "VAE",
-          "type": "VAE",
-          "slot_index": 2,
-          "links": [
-            18
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.18",
-        "Node name for S&R": "CheckpointLoaderSimple"
-      },
-      "widgets_values": [
-        "NoobAI-XL-Vpred-v1.0.safetensors"
-      ]
-    },
-    {
-      "id": 2,
-      "type": "PCLazyTextEncode",
-      "pos": [
-        555,
-        -720
-      ],
-      "size": [
-        252,
-        78
-      ],
-      "flags": {
-        "collapsed": true
-      },
-      "order": 7,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "clip",
-          "type": "CLIP",
-          "link": 5
-        },
-        {
-          "name": "text",
-          "type": "STRING",
-          "widget": {
-            "name": "text"
-          },
-          "link": 7
-        }
-      ],
-      "outputs": [
-        {
-          "name": "CONDITIONING",
-          "type": "CONDITIONING",
-          "slot_index": 0,
-          "links": [
-            12
-          ]
-        }
-      ],
-      "title": "PC: Schedule Prompt (positive)",
-      "properties": {
-        "cnr_id": "comfyui-prompt-control",
-        "ver": "2.0.0-beta.7",
-        "Node name for S&R": "PCLazyTextEncode"
-      },
-      "widgets_values": [
-        "STYLE(A1111) 1girl, [painting \\(medium\\), realistic,::0.2] fennec fox girl, animal ear fluff, [[purple:white pupils, purple:0.2] eyes:sparkling eyes:0.85], cargo pants, long sleeves, cardigan, winter, snow, steaming cup, coffee mug, [thermos,:0.1] [long hair,:0.25] [BREAK:0.3]\n[(masterpiece, best quality, newest, very awa,):0.1], night sky, full moon, star \\(sky\\),"
-      ],
-      "color": "#232",
-      "bgcolor": "#353"
-    },
-    {
-      "id": 3,
-      "type": "PCLazyLoraLoader",
-      "pos": [
-        257.5,
-        -745
-      ],
-      "size": [
-        210,
-        78
-      ],
-      "flags": {},
-      "order": 6,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "model",
-          "shape": 7,
-          "type": "MODEL",
-          "link": 2
-        },
-        {
-          "name": "clip",
-          "shape": 7,
-          "type": "CLIP",
-          "link": 3
-        },
-        {
-          "name": "text",
-          "type": "STRING",
-          "widget": {
-            "name": "text"
-          },
-          "link": 6
-        }
-      ],
-      "outputs": [
-        {
-          "name": "MODEL",
-          "type": "MODEL",
-          "slot_index": 0,
-          "links": [
-            17
-          ]
-        },
-        {
-          "name": "CLIP",
-          "type": "CLIP",
-          "slot_index": 1,
-          "links": [
-            5,
-            9
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfyui-prompt-control",
-        "ver": "2.0.0-beta.7",
-        "Node name for S&R": "PCLazyLoraLoader"
-      },
-      "widgets_values": [
-        "STYLE(A1111) 1girl, [painting \\(medium\\), realistic,::0.2] fennec fox girl, animal ear fluff, [[purple:white pupils, purple:0.2] eyes:sparkling eyes:0.85], cargo pants, long sleeves, cardigan, winter, snow, steaming cup, coffee mug, [thermos,:0.1] [long hair,:0.25] [BREAK:0.3]\n[(masterpiece, best quality, newest, very awa,):0.1], night sky, full moon, star \\(sky\\),"
-      ],
-      "color": "#223",
-      "bgcolor": "#335"
-    },
-    {
-      "id": 4,
-      "type": "KSampler",
-      "pos": [
-        930,
-        -780
-      ],
-      "size": [
-        315,
-        474
-      ],
-      "flags": {},
-      "order": 9,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "model",
-          "type": "MODEL",
-          "link": 17
-        },
-        {
-          "name": "positive",
-          "type": "CONDITIONING",
-          "link": 12
-        },
-        {
-          "name": "negative",
-          "type": "CONDITIONING",
-          "link": 13
-        },
-        {
-          "name": "latent_image",
-          "type": "LATENT",
-          "link": 14
-        }
-      ],
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "slot_index": 0,
-          "links": [
-            15
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.18",
-        "Node name for S&R": "KSampler"
-      },
-      "widgets_values": [
-        2,
-        "fixed",
-        25,
-        1.4000000000000001,
-        "euler_cfg_pp",
-        "simple",
-        1
-      ]
-    },
-    {
-      "id": 5,
-      "type": "PrimitiveNode",
-      "pos": [
-        -270,
-        -780
-      ],
-      "size": [
-        495,
-        225
-      ],
-      "flags": {},
-      "order": 1,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [
-        {
-          "name": "STRING",
-          "type": "STRING",
-          "widget": {
-            "name": "text"
-          },
-          "links": [
-            6,
-            7
-          ]
-        }
-      ],
-      "title": "Positive prompt (with LoRAs)",
-      "properties": {
-        "Run widget replace on values": false
-      },
-      "widgets_values": [
-        "STYLE(A1111) 1girl, [painting \\(medium\\), realistic,::0.2] fennec fox girl, animal ear fluff, [[purple:white pupils, purple:0.2] eyes:sparkling eyes:0.85], cargo pants, long sleeves, cardigan, winter, snow, steaming cup, coffee mug, [thermos,:0.1] [long hair,:0.25] [BREAK:0.3]\n[(masterpiece, best quality, newest, very awa,):0.1], night sky, full moon, star \\(sky\\),"
-      ],
-      "color": "#232",
-      "bgcolor": "#353"
-    },
-    {
-      "id": 6,
-      "type": "PrimitiveNode",
-      "pos": [
-        -270,
-        -510
-      ],
-      "size": [
-        480,
-        225
-      ],
-      "flags": {},
-      "order": 2,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [
-        {
-          "name": "STRING",
-          "type": "STRING",
-          "widget": {
-            "name": "text"
-          },
-          "slot_index": 0,
-          "links": [
-            8
-          ]
-        }
-      ],
-      "title": "Negative prompt",
-      "properties": {
-        "Run widget replace on values": false
-      },
-      "widgets_values": [
-        "chibi, [bad hands,low quality, worst quality,:0.05], simple background, blurry, sketch, unfinished, [holding two cups,no pupils,:0.1]"
-      ],
-      "color": "#322",
-      "bgcolor": "#533"
-    },
-    {
-      "id": 7,
-      "type": "PCLazyTextEncode",
-      "pos": [
-        555,
-        -675
-      ],
-      "size": [
-        252,
-        78
-      ],
-      "flags": {
-        "collapsed": true
-      },
-      "order": 8,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "clip",
-          "type": "CLIP",
-          "link": 9
-        },
-        {
-          "name": "text",
-          "type": "STRING",
-          "widget": {
-            "name": "text"
-          },
-          "link": 8
-        }
-      ],
-      "outputs": [
-        {
-          "name": "CONDITIONING",
-          "type": "CONDITIONING",
-          "slot_index": 0,
-          "links": [
-            13
-          ]
-        }
-      ],
-      "title": "PC: Schedule Prompt (negative)",
-      "properties": {
-        "cnr_id": "comfyui-prompt-control",
-        "ver": "2.0.0-beta.7",
-        "Node name for S&R": "PCLazyTextEncode"
-      },
-      "widgets_values": [
-        "chibi, [bad hands,low quality, worst quality,:0.05], simple background, blurry, sketch, unfinished, [holding two cups,no pupils,:0.1]"
-      ],
-      "color": "#322",
-      "bgcolor": "#533"
-    },
-    {
-      "id": 9,
-      "type": "EmptyLatentImage",
-      "pos": [
-        525,
-        -615
-      ],
-      "size": [
-        315,
-        106
-      ],
-      "flags": {},
-      "order": 3,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "links": [
-            14
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.18",
-        "Node name for S&R": "EmptyLatentImage"
-      },
-      "widgets_values": [
-        896,
-        1152,
-        1
-      ],
-      "color": "#432",
-      "bgcolor": "#653"
-    },
-    {
-      "id": 10,
-      "type": "VAEDecode",
-      "pos": [
-        1290,
-        -780
-      ],
-      "size": [
-        210,
-        46
-      ],
-      "flags": {},
-      "order": 10,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "samples",
-          "type": "LATENT",
-          "link": 15
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": 18
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "slot_index": 0,
-          "links": [
-            20
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.18",
-        "Node name for S&R": "VAEDecode"
-      },
-      "widgets_values": []
-    },
-    {
-      "id": 13,
-      "type": "MarkdownNote",
-      "pos": [
-        240,
-        -615
-      ],
-      "size": [
-        240,
-        105
-      ],
-      "flags": {},
-      "order": 4,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [],
-      "properties": {},
-      "widgets_values": [
-        "If you do not need LoRA scheduling, you can simply skip this node."
-      ],
-      "color": "#432",
-      "bgcolor": "#653"
-    },
-    {
-      "id": 15,
-      "type": "MarkdownNote",
-      "pos": [
-        240,
-        -450
-      ],
-      "size": [
-        600,
-        210
-      ],
-      "flags": {},
-      "order": 5,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [],
-      "properties": {},
-      "widgets_values": [
-        "`PC: Schedule prompt` will expand into instances of `PCTextEncode`. `PC: Schedule LoRAs` will expand into the required `LoRALoader`s and `CLIP` hooks required to schedule LoRAs in the prompt.\n\nYou can pass the same prompt to both nodes; `PC: Schedule Prompt` will simply ignore any `<lora:xyz:1>` elements, so they will not affect the prompt.\nSee the [full syntax available in the prompts](https://github.com/asagi4/comfyui-prompt-control/blob/master/doc/syntax.md) on GitHub"
-      ],
-      "color": "#432",
-      "bgcolor": "#653"
-    },
-    {
-      "id": 18,
-      "type": "SaveImage",
-      "pos": [
-        1290,
-        -690
-      ],
-      "size": [
-        270,
-        405
-      ],
-      "flags": {},
-      "order": 11,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 20
-        }
-      ],
-      "outputs": [],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.18"
-      },
-      "widgets_values": [
-        "PromptControl"
-      ]
-    }
-  ],
-  "links": [
-    [
-      2,
-      1,
-      0,
-      3,
-      0,
-      "MODEL"
-    ],
-    [
-      3,
-      1,
-      1,
-      3,
-      1,
-      "CLIP"
-    ],
-    [
-      5,
-      3,
-      1,
-      2,
-      0,
-      "CLIP"
-    ],
-    [
-      6,
-      5,
-      0,
-      3,
-      2,
-      "STRING"
-    ],
-    [
-      7,
-      5,
-      0,
-      2,
-      1,
-      "STRING"
-    ],
-    [
-      8,
-      6,
-      0,
-      7,
-      1,
-      "STRING"
-    ],
-    [
-      9,
-      3,
-      1,
-      7,
-      0,
-      "CLIP"
-    ],
-    [
-      12,
-      2,
-      0,
-      4,
-      1,
-      "CONDITIONING"
-    ],
-    [
-      13,
-      7,
-      0,
-      4,
-      2,
-      "CONDITIONING"
-    ],
-    [
-      14,
-      9,
-      0,
-      4,
-      3,
-      "LATENT"
-    ],
-    [
-      15,
-      4,
-      0,
-      10,
-      0,
-      "LATENT"
-    ],
-    [
-      17,
-      3,
-      0,
-      4,
-      0,
-      "MODEL"
-    ],
-    [
-      20,
-      10,
-      0,
-      18,
-      0,
-      "IMAGE"
-    ],
-    [
-      18,
-      1,
-      2,
-      10,
-      1,
-      "VAE"
-    ]
-  ],
-  "groups": [],
-  "config": {},
-  "extra": {
-    "ds": {
-      "scale": 0.8,
-      "offset": [
-        591.75,
-        1235
-      ]
-    },
-    "linkExtensions": [
-      {
-        "id": 18,
-        "parentId": 1
-      }
-    ],
-    "reroutes": [
-      {
-        "id": 1,
-        "pos": [
-          1273.75,
-          -879.5
-        ],
-        "linkIds": [
-          18
-        ]
-      }
-    ]
-  },
-  "version": 0.4,
-  "models": [{
-    "name": "NoobAI-XL-Vpred-v1.0.safetensors",
-    "url": "https://huggingface.co/Laxhar/noobai-XL-Vpred-1.0/resolve/main/NoobAI-XL-Vpred-v1.0.safetensors",
-    "directory": "checkpoints"
-  }]
-}

prompt_control/adv_encode.py

@@ -1,391 +0,0 @@
-import itertools
-import logging
-from math import copysign
-
-import numpy as np
-import torch
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def _norm_mag(w, n):
-    d = w - 1
-    return 1 + np.sign(d) * np.sqrt(np.abs(d) ** 2 / n)
-    # return  np.sign(w) * np.sqrt(np.abs(w)**2 / n)
-
-
-def _grouper(n, iterable):
-    it = iter(iterable)
-    while True:
-        chunk = list(itertools.islice(it, n))
-        if not chunk:
-            return
-        yield chunk
-
-
-def batched_clip_encode(tokens, length, encode_func, num_chunks):
-    embs = []
-    for e in _grouper(32, tokens):
-        enc, pooled, *_ = encode_func(e)
-        enc = enc.reshape((len(e), length, -1))
-        embs.append(enc)
-
-    embs = torch.cat(embs)
-    embs = embs.reshape((len(tokens) // num_chunks, length * num_chunks, -1))
-    return embs
-
-
-def weights_like(weights, emb):
-    return torch.tensor(weights, dtype=emb.dtype, device=emb.device).reshape(1, -1, 1).expand(emb.shape)
-
-
-def scale_to_norm(weights, word_ids, w_max):
-    top = np.max(weights)
-    w_max = min(top, w_max)
-    weights = [
-        [w_max if id == 0 else (w / top) * w_max for w, id in zip(x, y, strict=False)]
-        for x, y in zip(weights, word_ids, strict=False)
-    ]
-    return weights
-
-
-def mask_word_id(tokens, word_ids, target_id, mask_token):
-    new_tokens = [
-        [mask_token if wid == target_id else t for t, wid in zip(x, y, strict=False)]
-        for x, y in zip(tokens, word_ids, strict=False)
-    ]
-    mask = np.array(word_ids) == target_id
-    return (new_tokens, mask)
-
-
-def mask_inds(tokens, inds, mask_token):
-    clip_len = len(tokens[0])
-    inds_set = set(inds)
-    new_tokens = [
-        [mask_token if i * clip_len + j in inds_set else t for j, t in enumerate(x)] for i, x in enumerate(tokens)
-    ]
-    return new_tokens
-
-
-def scale_emb_to_mag(base_emb, weighted_emb):
-    norm_base = torch.linalg.norm(base_emb)
-    norm_weighted = torch.linalg.norm(weighted_emb)
-    embeddings_final = (norm_base / norm_weighted) * weighted_emb
-    return embeddings_final
-
-
-def perp_weight(weights, unweighted_embs, empty_embs):
-    unweighted, unweighted_pooled = unweighted_embs
-    zero, zero_pooled = empty_embs
-
-    weights = weights_like(weights, unweighted)
-
-    if zero.shape != unweighted.shape:
-        zero = zero.repeat(1, unweighted.shape[1] // zero.shape[1], 1)
-
-    perp = (
-        torch.mul(zero, unweighted).sum(dim=-1, keepdim=True) / (unweighted.norm(dim=-1, keepdim=True) ** 2)
-    ) * unweighted
-
-    over1 = weights.abs() > 1.0
-    result = unweighted + weights * perp
-    result[~over1] = (unweighted - (1 - weights) * perp)[~over1]
-    result[weights == 0.0] = zero[weights == 0.0]
-
-    # Not sure if this is an implementation bug or if this just doesn't make sense with T5
-    nans = result.isnan()
-    if nans.any():
-        log.warning("perp weight returned NaNs (known to happen with T5), replacing with 0")
-        result[nans] = 0.0
-
-    return result, unweighted_pooled
-
-
-def style_comfy(encoder, tokens, **kwargs):
-    tokens = encoder.without_word_ids(tokens)
-    return encoder.encode_fn(tokens)
-
-
-def style_a1111(encoder, tokens, **kwargs):
-    base_emb, pooled, *extra = encoder.base_emb(tokens)
-    weighted_emb = base_emb * weights_like(encoder.weights(tokens), base_emb)
-    weighted_emb = (base_emb.mean() / weighted_emb.mean()) * weighted_emb  # renormalize
-    return (weighted_emb, pooled) + tuple(extra)
-
-
-def style_compel(encoder, tokens, **kwargs):
-    pos_tokens = encoder.weighted_with(tokens, lambda w: w if w > 1.0 else 1.0)
-    weighted_emb, pooled, *extra = encoder.encode_fn(pos_tokens)
-    weighted_emb, _, pooled = encoder.down_weight(
-        pos_tokens, encoder.weights(tokens), encoder.word_ids(tokens), weighted_emb, pooled
-    )
-    return (weighted_emb, pooled) + tuple(extra)
-
-
-def style_comfypp(encoder, tokens, **kwargs):
-    unweighted_tokens = encoder.unweighted(tokens)
-    base_emb, pooled_base, *extra = encoder.base_emb(tokens)
-    weighted_emb, tokens_down, _ = encoder.down_weight(
-        unweighted_tokens, encoder.weights(tokens), encoder.word_ids(tokens), base_emb, pooled_base
-    )
-    weights = encoder.weights(encoder.weighted_with(tokens, lambda w: w if w > 1.0 else 1.0))
-    embs, pooled = encoder.from_masked(
-        unweighted_tokens,
-        weights,
-        encoder.word_ids(tokens),
-        base_emb,
-        pooled_base,
-    )
-    weighted_emb += embs
-
-    return (weighted_emb, pooled) + tuple(extra)
-
-
-def style_downweight(encoder, tokens, **kwargs):
-    weights = scale_to_norm(encoder.weights(tokens), encoder.word_ids(tokens), encoder.w_max)
-    base_emb, pooled_base, *extra = encoder.base_emb(tokens)
-    weighted_emb, _, pooled = encoder.down_weight(
-        encoder.unweighted(tokens), weights, encoder.word_ids(tokens), base_emb, pooled_base
-    )
-
-    return (weighted_emb, pooled) + tuple(extra)
-
-
-def style_perp(encoder, tokens, **kwargs):
-    zero_emb, zero_pooled, *_ = encoder.encode_fn(encoder.tokenizer.tokenize_with_weights(""))
-    base_emb, pooled, *extra = encoder.base_emb(tokens)
-    return perp_weight(encoder.weights(tokens), (base_emb, pooled), (zero_emb, zero_pooled)) + tuple(extra)
-
-
-def apply_negpip(encoder, emb, pooled, **kwargs):
-    original_tokens = kwargs["original_tokens"]
-    emb_negpip = torch.empty_like(emb).repeat(1, 2, 1)
-    emb_negpip[:, 0::2, :] = emb
-    emb_negpip[:, 1::2, :] = emb * weights_like(encoder.signs(original_tokens), emb)
-    return emb_negpip, pooled
-
-
-def norm_length(encoder, tokens, **kwargs):
-    word_ids = encoder.word_ids(tokens)
-    sums = dict(zip(*np.unique(word_ids, return_counts=True), strict=False))
-    sums[0] = 1
-    tokens = [[(t, _norm_mag(w, sums[id]) if id != 0 else 1.0, id) for (t, w, id) in x] for x in tokens]
-    return tokens
-
-
-def norm_mean(encoder, tokens, **kwargs):
-    weights = encoder.weights(tokens)
-    word_ids = encoder.word_ids(tokens)
-    delta = 1 - np.mean(
-        [w for x, y in zip(weights, word_ids, strict=False) for w, id in zip(x, y, strict=False) if id != 0]
-    )
-    tokens = [[(t, w if id == 0 else w + delta, id) for (t, w, id) in x] for x in tokens]
-    return tokens
-
-
-def norm_none(encoder, tokens, **kwargs):
-    return tokens
-
-
-class AdvancedEncoder:
-    STYLES = {
-        "A1111": style_a1111,
-        "comfy": style_comfy,
-        "comfy++": style_comfypp,
-        "compel": style_compel,
-        "down_weight": style_downweight,
-        "perp": style_perp,
-    }
-    NORMALIZATION_OPS = {
-        "none": norm_none,
-        "length": norm_length,
-        "mean": norm_mean,
-    }
-
-    @classmethod
-    def add_encoder(cls, name, fn):
-        cls.STYLES[name] = fn
-
-    @classmethod
-    def add_normalization_op(cls, name, fn):
-        cls.NORMALIZATION_OPS[name] = fn
-
-    @classmethod
-    def weighted_with(cls, tokens, fn=id, word_ids=True):
-        w = ([(t, fn(w), id) for t, w, id in x] for x in tokens)
-        if not word_ids:
-            w = cls.without_word_ids(w)
-        return list(w)
-
-    @classmethod
-    def unweighted(cls, tokens, word_ids=False):
-        return cls.weighted_with(tokens, fn=lambda w: 1.0, word_ids=word_ids)
-
-    @classmethod
-    def tokens_only(cls, tokens):
-        return list([t[0] for t in x] for x in tokens)
-
-    @classmethod
-    def weights(cls, tokens):
-        return list([t[1] for t in x] for x in tokens)
-
-    @classmethod
-    def word_ids(cls, tokens):
-        return list([t[2] for t in x] for x in tokens)
-
-    @classmethod
-    def signs(cls, tokens):
-        return list([copysign(1, t[1]) for t in x] for x in tokens)
-
-    @classmethod
-    def without_word_ids(cls, tokens):
-        return list([(t, w) for t, w, _ in x] for x in tokens)
-
-    def __init__(self, encode_fn, style, normalization, tokenizer, m_token="+", w_max=1.0, **extra_args):
-        self.encode_fn = encode_fn
-        self.preprocessors = []
-        self.postprocessors = []
-        self.tokenizer = tokenizer
-        self.extra_args = extra_args
-        self.m_token = tokenizer.tokenize_with_weights(m_token)[0][tokenizer.tokens_start]
-        self.max_length = tokenizer.max_length if tokenizer.pad_to_max_length else None
-        self.w_max = w_max
-
-        if style == "comfy++" and not self.max_length:
-            log.warning("comfy++ does not work with tokenizer %s, using default weighting", tokenizer)
-            style = "comfy"
-
-        norms = normalization.split("+")
-        assert style in self.STYLES, f"Invalid weight interpretation: {style}"
-        self.weight_fn = self.STYLES[style]
-        for n in norms:
-            n = n.strip()
-            assert n in self.NORMALIZATION_OPS, f"Invalid normalization: {normalization}"
-            self.preprocessors.append(self.NORMALIZATION_OPS[n])
-
-        negpip = extra_args.get("has_negpip")
-        if negpip:
-
-            def _encode(t):
-                emb, pooled, *extra = encode_fn(t)
-                return (emb[:, 0::2, :], pooled) + tuple(extra)
-
-            self.encode_fn = _encode
-            self.preprocessors.insert(0, lambda encoder, tokens, **kwargs: encoder.weighted_with(tokens, abs))
-            self.postprocessors.insert(0, apply_negpip)
-
-    def base_emb(self, tokens):
-        unweighted = self.unweighted(tokens)
-        return self.encode_fn(unweighted)
-
-    def down_weight(self, tokens, weights, word_ids, base_emb, pooled_base):
-        w, w_inv = np.unique(weights, return_inverse=True)
-
-        if np.sum(w < 1) == 0:
-            return (
-                base_emb,
-                tokens,
-                (
-                    base_emb[0, self.max_length - 1 : self.max_length, :]
-                    if (pooled_base is not None and self.max_length)
-                    else None
-                ),
-            )
-
-        masked_current = tokens
-        emblist = [base_emb]
-        for i in range(len(w)):
-            if w[i] >= 1:
-                continue
-            masked_current = mask_inds(masked_current, np.where(w_inv == i)[0], self.m_token)
-            masked, _, *extra = self.encode_fn(masked_current)
-            emblist.append(masked)
-
-        embs = torch.cat(emblist)
-        w = w[w <= 1.0]
-        w_mix = np.diff([0] + w.tolist())
-        w_mix = torch.tensor(w_mix, dtype=embs.dtype, device=embs.device).reshape((-1, 1, 1))
-
-        weighted_emb = (w_mix * embs).sum(dim=0, keepdim=True)
-        pooled = pooled_base
-        if pooled is not None and self.max_length:
-            pooled = weighted_emb[0, self.max_length - 1 : self.max_length, :]
-        return weighted_emb, masked_current, pooled
-
-    def from_masked(self, tokens, weights, word_ids, base_emb, pooled_base):
-        wids, inds = np.unique(np.array(word_ids).reshape(-1), return_index=True)
-        weight_dict = dict(
-            (id, w) for id, w in zip(wids, np.array(weights).reshape(-1)[inds], strict=False) if w != 1.0
-        )
-
-        if len(weight_dict) == 0:
-            return torch.zeros_like(base_emb), torch.zeros_like(pooled_base) if pooled_base is not None else None
-
-        weight_tensor = weights_like(weights, base_emb)
-
-        ws = []
-        masked_tokens = []
-        masks = []
-
-        # create prompts
-        for id, w in weight_dict.items():
-            masked, m = mask_word_id(tokens, word_ids, id, self.m_token)
-            masks.append(weights_like(m, base_emb))
-            masked_tokens.extend(masked)
-
-            ws.append(w)
-
-        # TODO: figure out how to get rid of this
-        embs = batched_clip_encode(masked_tokens, self.max_length, self.encode_fn, len(tokens))
-        masks = torch.cat(masks)
-
-        embs = base_emb.expand(embs.shape) - embs
-        pooled = None
-        if pooled_base is not None and self.max_length:
-            pooled = embs[0, self.max_length - 1 : self.max_length, :]
-            pooled_start = pooled_base.expand(len(ws), -1)
-            ws = torch.tensor(ws).reshape(-1, 1).expand(pooled_start.shape)
-            pooled = (pooled - pooled_start) * (ws - 1)
-            pooled = pooled.mean(dim=0, keepdim=True)
-            pooled = pooled_base + pooled
-
-        if embs.shape[0] != masks.shape[0]:
-            embs = embs.repeat(masks.shape[0], 1, 1)
-        embs *= masks
-        embs = embs.sum(axis=0, keepdim=True)
-
-        return ((weight_tensor - 1) * embs), pooled
-
-    def __call__(self, tokens, apply_to_pooled=False, return_pooled=False):
-        normalized_tokens = tokens
-        for op in self.preprocessors:
-            normalized_tokens = op(self, normalized_tokens)
-
-        emb, pooled, *extra = self.weight_fn(self, normalized_tokens, original_tokens=tokens)
-
-        for fn in self.postprocessors:
-            emb, pooled = fn(self, emb, pooled, tokens=tokens, original_tokens=tokens)
-
-        if not return_pooled:
-            pooled = None
-        elif not apply_to_pooled:
-            _, pooled, *_ = self.base_emb(tokens)
-        return (emb, pooled) + tuple(extra)
-
-
-def advanced_encode_from_tokens(
-    tokenized,
-    token_normalization,
-    weight_interpretation,
-    encode_func,
-    m_token="+",
-    w_max=1.0,
-    return_pooled=False,
-    apply_to_pooled=False,
-    tokenizer=None,
-    **extra_args,
-):
-    enc = AdvancedEncoder(
-        encode_func, weight_interpretation, token_normalization, tokenizer, m_token, w_max, **extra_args
-    )
-    return enc(tokenized, return_pooled=return_pooled, apply_to_pooled=apply_to_pooled)

prompt_control/anima_couple.py

@@ -1,167 +0,0 @@
-# Adapted from https://github.com/pamparamm/ComfyUI-ppm
-import itertools
-from collections.abc import Callable
-from functools import partial
-from math import lcm
-
-import torch
-import torch.nn.functional as F
-from comfy.ldm.anima.model import Anima as AnimaDIT
-from comfy.ldm.cosmos.predict2 import Attention as CosmosAttention
-from comfy.patcher_extension import WrapperExecutor
-from comfy.sampler_helpers import convert_cond
-from comfy.samplers import process_conds
-
-COND = 0
-UNCOND = 1
-
-
-def reshape_mask(mask: torch.Tensor, size: tuple[int, int], bs: int, num_tokens: int) -> torch.Tensor:
-    num_conds = mask.shape[0]
-
-    mask_downsample = F.interpolate(mask, size=size, mode="nearest")
-    mask_downsample_reshaped = mask_downsample.view(num_conds, num_tokens, 1).repeat_interleave(bs, dim=0)
-
-    return mask_downsample_reshaped
-
-
-def wrap_forwards(anima_model):
-    backups = {}
-    for block_name, b in (
-        (n, b) for n, b in anima_model.named_modules() if "cross_attn" in n and isinstance(b, CosmosAttention)
-    ):
-        backups[block_name] = b.forward
-        b.forward = partial(cosmos_attention_forward_couple, b.forward)
-    return backups
-
-
-def unwrap_forwards(anima_model, backups):
-    for block_name, b in (
-        (n, b) for n, b in anima_model.named_modules() if "cross_attn" in n and isinstance(b, CosmosAttention)
-    ):
-        b.forward = backups[block_name]
-
-
-def anima_sample_wrapper(executor, *args, **kwargs):
-    guider, _, extra_options, _, noise, latent_image, denoise_mask, *_ = args
-    seed = extra_options["seed"]
-    device = "cuda"  # TODO: fix
-
-    def pc_process_conds(pc_conds):
-        conds = [convert_cond([c])[0] for c in pc_conds]
-        conds = process_conds(
-            guider.inner_model,
-            noise,
-            {"positive": conds},
-            device,
-            latent_image,
-            denoise_mask,
-            seed,
-            latent_shapes=[latent_image.shape],
-        )
-        return [
-            c["model_conds"]["c_crossattn"].cond * pc_conds[i][1].get("strength", 1.0)
-            for i, c in enumerate(conds["positive"])
-        ]
-
-    extra_options["model_options"]["transformer_options"]["pc_process_conds"] = pc_process_conds
-    return executor(*args, **kwargs)
-
-
-def anima_forward_wrapper(executor: WrapperExecutor, *args, **kwargs):
-    """Model wrapper does something with activation shapes?"""
-    anima_model: AnimaDIT = executor.class_obj  # type: ignore
-
-    x: torch.Tensor = args[0]
-    transformer_options: dict = kwargs.get("transformer_options", {}).copy()
-    pc = transformer_options.get("pc_couple")
-    if pc and "processed_conds" not in pc:
-        pc["processed_conds"] = transformer_options["pc_process_conds"](pc["conds"])
-    patch_spatial = anima_model.patch_spatial
-
-    activations_shape = list(x.shape)
-    activations_shape[-2] = activations_shape[-2] // patch_spatial
-    activations_shape[-1] = activations_shape[-1] // patch_spatial
-
-    transformer_options["activations_shape"] = activations_shape
-    kwargs["transformer_options"] = transformer_options
-
-    b = {}
-    if pc:
-        b = wrap_forwards(anima_model)
-    r = executor(*args, **kwargs)
-    if pc:
-        unwrap_forwards(anima_model, b)
-    return r
-
-
-def cosmos_attention_forward_couple(_forward: Callable, x, context, rope_emb, transformer_options):
-    """attention block wrapper"""
-    if "pc_couple" not in transformer_options:
-        return _forward(x, context, rope_emb, transformer_options)
-    c: torch.Tensor = context
-    # FIXME: base cond weight
-    # c = args["processed_conds"][0]
-
-    args = transformer_options["pc_couple"]
-
-    mask = args["mask"]
-    conds = args["processed_conds"][1:]
-    num_conds = len(conds) + 1
-    num_tokens_c: list[int] = [c.shape[1] for c in conds]
-    cond_or_uncond = transformer_options["cond_or_uncond"]
-    cond_or_uncond_couple = []
-
-    num_chunks = len(cond_or_uncond)
-    bs = x.shape[0] // num_chunks
-
-    x_chunks = x.chunk(num_chunks, dim=0)
-    c_chunks = c.chunk(num_chunks, dim=0)
-    lcm_tokens_c = lcm(c.shape[1], *num_tokens_c)
-    conds_c_tensor = torch.cat(
-        [cond.repeat(bs, lcm_tokens_c // num_tokens_c[i], 1) for i, cond in enumerate(conds)],
-        dim=0,
-    )
-
-    xs, cs = [], []
-    for i, cond_type in enumerate(cond_or_uncond):
-        x_target = x_chunks[i]
-        c_target = c_chunks[i].repeat(1, lcm_tokens_c // c.shape[1], 1)
-        if cond_type == UNCOND:
-            xs.append(x_target)
-            cs.append(c_target)
-            cond_or_uncond_couple.append(UNCOND)
-        else:
-            xs.append(x_target.repeat(num_conds, 1, 1))
-            cs.append(torch.cat([c_target, conds_c_tensor], dim=0))
-            cond_or_uncond_couple.extend(itertools.repeat(COND, num_conds))
-
-    xs = torch.cat(xs, dim=0)
-    cs = torch.cat(cs, dim=0)
-
-    out = _forward(xs, cs, rope_emb, transformer_options)
-
-    size = tuple(transformer_options["activations_shape"][-2:])
-    num_tokens = out.shape[1]
-    mask_downsample = reshape_mask(mask, size, bs, num_tokens)
-
-    outputs = []
-    cond_outputs = []
-    i_cond = 0
-
-    for i, cond_type in enumerate(cond_or_uncond_couple):
-        pos, next_pos = i * bs, (i + 1) * bs
-
-        if cond_type == UNCOND:
-            outputs.append(out[pos:next_pos])
-        else:
-            pos_cond, next_pos_cond = i_cond * bs, (i_cond + 1) * bs
-            masked_output = out[pos:next_pos] * mask_downsample[pos_cond:next_pos_cond]
-            cond_outputs.append(masked_output)
-            i_cond += 1
-
-    if len(cond_outputs) > 0:
-        cond_output = torch.stack(cond_outputs).sum(0)
-        outputs.append(cond_output)
-
-    return torch.cat(outputs, dim=0)

prompt_control/attention_couple_ppm.py

@@ -1,255 +0,0 @@
-# Lifted from https://github.com/pamparamm/ComfyUI-ppm/blob/c3e6b673ee2d424405dcb99aeed89f21943c89ac/nodes_ppm/attention_couple_ppm.py
-# Original implementation by laksjdjf, hako-mikan, Haoming02 licensed under GPL-3.0
-# https://github.com/laksjdjf/cgem156-ComfyUI/blob/1f5533f7f31345bafe4b833cbee15a3c4ad74167/scripts/attention_couple/node.py
-# https://github.com/Haoming02/sd-forge-couple/blob/e8e258e982a8d149ba59a4bc43b945467604311c/scripts/attention_couple.py
-import itertools
-import logging
-import math
-from typing import Any
-
-import torch
-import torch.nn.functional as F
-from comfy.hooks import EnumHookScope, HookGroup, TransformerOptionsHook, set_hooks_for_conditioning
-from comfy.model_patcher import ModelPatcher
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def set_cond_attnmask(base_cond, extra_conds, fill=False):
-    hook = AttentionCoupleHook()
-    c = [base_cond[0][0], base_cond[0][1].copy()]
-    # hook uses these, remove them to avoid doing latent masking
-    c[1].pop("mask", None)
-    c[1].pop("strength", None)
-    c[1].pop("mask_strength", None)
-    c = [c]
-    c.extend(base_cond[1:])
-
-    hook.initialize_regions(base_cond[0], extra_conds, fill=fill)
-    group = HookGroup()
-    group.add(hook)
-
-    return set_hooks_for_conditioning(c, hooks=group, append_hooks=True)
-
-
-def get_mask(mask, batch_size, num_tokens, extra_options):
-    activations_shape = extra_options["activations_shape"]
-    size = activations_shape[-2:]
-
-    num_conds = mask.shape[0]
-    mask_downsample = F.interpolate(mask, size=size, mode="nearest")
-    mask_downsample_reshaped = mask_downsample.view(num_conds, num_tokens, 1).repeat_interleave(batch_size, dim=0)
-
-    return mask_downsample_reshaped
-
-
-class Proxy:
-    def __init__(self, function):
-        self.function = function
-
-    def to(self, *args, **kwargs):
-        self.function.__self__.to(*args, **kwargs)
-        return self
-
-    def __call__(self, *args, **kwargs):
-        return self.function(*args, **kwargs)
-
-
-class AttentionCoupleHook(TransformerOptionsHook):
-    COND_UNCOND_COUPLE_OPTION = "cond_or_uncond_hook_couple"
-    COND = 0
-    UNCOND = 1
-
-    def __init__(self):
-        super().__init__(hook_scope=EnumHookScope.HookedOnly)
-
-        self.transformers_dict: dict[str, Any] = {
-            "patches": {
-                "attn2_output_patch": [Proxy(self.attn2_output_patch)],
-                "attn2_patch": [Proxy(self.attn2_patch)],
-            },
-            "pc_couple": {},
-        }
-
-        self.has_negpip = False
-        # The list will be calculated later. All clones must refer to the same kv dict
-        self.kv: dict[str, list] = {"k": None, "v": None}  # type: ignore
-
-    def initialize_regions(self, base_cond, conds, fill):
-        self.num_conds = len(conds) + 1
-        self.base_strength = base_cond[1].get("strength", 1.0)
-        self.strengths: list[float] = [cond[1].get("strength", 1.0) for cond in conds]
-        self.comfy_conds = [base_cond] + conds
-        self.conds: list[torch.Tensor] = [base_cond[0]] + [cond[0] for cond in conds]
-        base_mask = base_cond[1].get("mask", None)
-        masks = [cond[1].get("mask") * cond[1].get("mask_strength") for cond in conds]
-        if len(masks) < 1:
-            raise ValueError("Attention Couple hook makes no sense without masked conds")
-
-        if any(m is None for m in masks):
-            raise ValueError("All conds given to Attention Couple must have masks")
-
-        if any(m.shape != masks[0].shape for m in masks) or (
-            base_mask is not None and base_mask.shape != masks[0].shape
-        ):
-            largest_shape = max(m.shape for m in masks)
-            if base_mask is not None:
-                largest_shape = max(largest_shape, base_mask.shape)
-            log.warning("Attention Couple: Masks are irregularly shaped, resizing them all to match the largest")
-            for i in range(len(masks)):
-                masks[i] = F.interpolate(masks[i].unsqueeze(1), size=largest_shape[1:], mode="nearest-exact").squeeze(1)
-
-            if base_mask is not None:
-                base_mask = F.interpolate(base_mask.unsqueeze(1), size=largest_shape[1:], mode="nearest-exact").squeeze(
-                    1
-                )
-
-        if base_mask is None:
-            if not fill:
-                raise ValueError("You must specify a base mask when fill=False")
-            sum = torch.stack(masks, dim=0).sum(dim=0)
-            base_mask = torch.zeros_like(sum)
-            base_mask[sum <= 0] = 1.0
-
-        mask = [base_mask] + masks
-        mask = torch.stack(mask, dim=0)
-        if mask.sum(dim=0).min() <= 0 and not fill:
-            raise ValueError("Masks contain non-filled areas")
-
-        self.mask = mask / mask.sum(dim=0, keepdim=True)
-
-    def on_apply_hooks(self, model: ModelPatcher, transformer_options: dict[str, Any]):
-        self.transformers_dict["pc_couple"] = {
-            "conds": self.comfy_conds,
-            "num_conds": self.num_conds,
-            "mask": self.mask,
-        }
-        if self.kv["k"] is None:
-            self.has_negpip = model.model_options.get("ppm_negpip", False)
-            log.debug("AttentionCouple has_negpip=%s", self.has_negpip)
-
-            # Skip the base cond here, which is always first
-            if self.has_negpip:
-                self.kv["k"] = [cond[:, 0::2] for cond in self.conds[1:]]
-                self.kv["v"] = [cond[:, 1::2] for cond in self.conds[1:]]
-            else:
-                self.kv["k"] = self.kv["v"] = self.conds[1:]
-
-        return super().on_apply_hooks(model, transformer_options)
-
-    def clone(self):
-        c: AttentionCoupleHook = super().clone()
-        c.mask = self.mask
-        c.conds = self.conds
-        c.kv = self.kv
-        c.has_negpip = self.has_negpip
-        c.base_strength = self.base_strength
-        c.strengths = self.strengths
-        c.num_conds = self.num_conds
-        return c
-
-    def to(self, *args, **kwargs):
-        self.conds = [c.to(*args, **kwargs) for c in self.conds]
-        self.mask = self.mask.to(*args, **kwargs)
-        if self.kv["k"] is not None:
-            self.kv["k"] = [c.to(*args, **kwargs) for c in self.kv["k"]]
-            self.kv["v"] = [c.to(*args, **kwargs) for c in self.kv["v"]]
-        return self
-
-    def attn2_patch(self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, extra_options):
-        cond_or_uncond = extra_options["cond_or_uncond"]
-        cond_or_uncond_couple = extra_options[self.COND_UNCOND_COUPLE_OPTION] = list(cond_or_uncond)
-        num_chunks = len(cond_or_uncond)
-
-        # Cloning messes up the device sometimes
-        if self.kv["k"][0].device != k.device:
-            self.to(k)
-
-        conds_k = self.kv["k"]
-        conds_v = self.kv["v"]
-
-        lcm_tokens_k = math.lcm(k.shape[1], *(cond.shape[1] for cond in conds_k))
-        lcm_tokens_v = math.lcm(v.shape[1], *(cond.shape[1] for cond in conds_v))
-        q_chunks = q.chunk(num_chunks, dim=0)
-        k_chunks = k.chunk(num_chunks, dim=0)
-        v_chunks = v.chunk(num_chunks, dim=0)
-
-        bs = q.shape[0] // num_chunks
-
-        conds_k_tensor = conds_v_tensor = torch.cat(
-            [cond.repeat(bs, lcm_tokens_k // cond.shape[1], 1) * self.strengths[i] for i, cond in enumerate(conds_k)],
-            dim=0,
-        )
-        if self.has_negpip:
-            conds_v_tensor = torch.cat(
-                [
-                    cond.repeat(bs, lcm_tokens_v // cond.shape[1], 1) * self.strengths[i]
-                    for i, cond in enumerate(conds_v)
-                ],
-                dim=0,
-            )
-
-        qs, ks, vs = [], [], []
-        cond_or_uncond_couple.clear()
-
-        for i, cond_type in enumerate(cond_or_uncond):
-            q_target = q_chunks[i]
-            k_target = k_chunks[i].repeat(1, lcm_tokens_k // k.shape[1], 1)
-            v_target = v_chunks[i].repeat(1, lcm_tokens_v // v.shape[1], 1)
-            if cond_type == self.UNCOND:
-                qs.append(q_target)
-                ks.append(k_target)
-                vs.append(v_target)
-                cond_or_uncond_couple.append(self.UNCOND)
-            else:
-                qs.append(q_target.repeat(self.num_conds, 1, 1))
-                ks.append(
-                    torch.cat(
-                        [
-                            k_target * self.base_strength,
-                            conds_k_tensor,
-                        ],
-                        dim=0,
-                    )
-                )
-                vs.append(
-                    torch.cat(
-                        [
-                            v_target * self.base_strength,
-                            conds_v_tensor,
-                        ],
-                        dim=0,
-                    )
-                )
-                assert self.num_conds is not None, "this is a bug"
-                cond_or_uncond_couple.extend(itertools.repeat(self.COND, self.num_conds))
-
-        q = torch.cat(qs, dim=0)
-        k = torch.cat(ks, dim=0)
-        v = torch.cat(vs, dim=0)
-
-        return q, k, v
-
-    def attn2_output_patch(self, out, extra_options):
-        cond_or_uncond = extra_options[self.COND_UNCOND_COUPLE_OPTION]
-        bs = out.shape[0] // len(cond_or_uncond)
-        mask_downsample = get_mask(self.mask, bs, out.shape[1], extra_options)
-        outputs = []
-        cond_outputs = []
-        i_cond = 0
-        for i, cond_type in enumerate(cond_or_uncond):
-            pos, next_pos = i * bs, (i + 1) * bs
-
-            if cond_type == self.UNCOND:
-                outputs.append(out[pos:next_pos])
-            else:
-                pos_cond, next_pos_cond = i_cond * bs, (i_cond + 1) * bs
-                masked_output = out[pos:next_pos] * mask_downsample[pos_cond:next_pos_cond]
-                cond_outputs.append(masked_output)
-                i_cond += 1
-
-        if len(cond_outputs) > 0:
-            cond_output = torch.stack(cond_outputs).sum(0)
-            outputs.append(cond_output)
-
-        return torch.cat(outputs, dim=0)

prompt_control/cutoff.py

@@ -1,228 +0,0 @@
-import copy
-import logging
-import re
-
-import numpy as np
-import torch
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def replace_embeddings(max_token, prompt, replacements=None):
-    """Replaces embedding tensors in a token array and replaces them with increasing IDs past max_token"""
-
-    if replacements is None:
-        emb_lookup = []
-    else:
-        emb_lookup = replacements.copy()
-        max_token += len(emb_lookup)
-
-    def get_replacement(embedding):
-        for e, n in emb_lookup:
-            if torch.equal(embedding, e):
-                return n
-        return None
-
-    tokens = []
-    for x in prompt:
-        row = []
-        for i in range(len(x)):
-            emb = x[i][0]
-            if not torch.is_tensor(emb):
-                row.append(emb)
-            else:
-                n = get_replacement(emb)
-                if n is not None:
-                    row.append(n)
-                else:
-                    max_token += 1
-                    row.append(max_token)
-                    emb_lookup.append((emb, max_token))
-        tokens.append(row)
-    tokens = np.array(tokens)[:, 1:-1].reshape(-1)
-    return (tokens, emb_lookup)
-
-
-def unpad_prompt(pad_token, prompt):
-    res = np.trim_zeros(prompt, "b")
-    return np.trim_zeros(res - pad_token, "b") + pad_token
-
-
-def get_sublists(super_list, sub_list):
-    positions = []
-    for candidate_ind in (i for i, e in enumerate(super_list) if e == sub_list[0]):
-        if super_list[candidate_ind : candidate_ind + len(sub_list)] == sub_list:
-            positions.append(candidate_ind)
-    return positions
-
-
-def cutoff_add_region(
-    clip_regions, tokenizer, region_text, target_text, weight, strict_mask, start_from_masked, mask_token
-):
-    """Adds a cut region to the clip_regions dictionary. It is modified in place"""
-    base_tokens = clip_regions["base_tokens"]
-    region_outputs = []
-    target_outputs = []
-    if strict_mask is not None:
-        clip_regions["strict_mask"] = float(strict_mask)
-    if start_from_masked is not None:
-        clip_regions["start_from_masked"] = float(start_from_masked)
-    if mask_token is not None:
-        clip_regions["mask_token"] = tokenizer.tokenizer(mask_token)["input_ids"][1]
-    weight = 1.0 if weight is None else float(weight)
-
-    region_text = region_text.strip()
-    target_text = target_text.strip()
-
-    strict_mask = clip_regions["strict_mask"]
-    start_from_masked = clip_regions["start_from_masked"]
-    mask_token = clip_regions["mask_token"]
-    log.info(f"CUT region {region_text=} {target_text=} {weight=} {strict_mask=} {start_from_masked=} {mask_token=}")
-
-    pad_token = tokenizer.end_token
-
-    prompt_tokens, emb_lookup = replace_embeddings(pad_token, base_tokens)
-
-    for rt in region_text.split("\n"):
-        region_tokens = tokenizer.tokenize_with_weights(rt)
-        region_tokens, _ = replace_embeddings(pad_token, region_tokens, emb_lookup)
-        region_tokens = unpad_prompt(pad_token, region_tokens).tolist()
-
-        # calc region mask
-        region_length = len(region_tokens)
-        regions = get_sublists(list(prompt_tokens), region_tokens)
-
-        region_mask = np.zeros(len(prompt_tokens))
-        for r in regions:
-            region_mask[r : r + region_length] = 1
-        region_mask = region_mask.reshape(-1, tokenizer.max_length - 2)
-        region_mask = np.pad(region_mask, pad_width=((0, 0), (1, 1)), mode="constant", constant_values=0)
-        region_mask = region_mask.reshape(1, -1)
-        region_outputs.append(region_mask)
-
-        # calc target mask
-        targets = []
-        for target in target_text.split(" "):
-            # deal with underscores
-            target = re.sub(r"(?<!\\)_", " ", target)
-            target = re.sub(r"\\_", "_", target)
-
-            target_tokens = tokenizer.tokenize_with_weights(target)
-            target_tokens, _ = replace_embeddings(pad_token, target_tokens, emb_lookup)
-            target_tokens = unpad_prompt(pad_token, target_tokens).tolist()
-
-            targets.extend([(x, len(target_tokens)) for x in get_sublists(region_tokens, target_tokens)])
-        targets = [(t_start + r, t_start + t_end + r) for r in regions for t_start, t_end in targets]
-
-        targets_mask = np.zeros(len(prompt_tokens))
-        for t_start, t_end in targets:
-            targets_mask[t_start:t_end] = 1
-        targets_mask = targets_mask.reshape(-1, tokenizer.max_length - 2)
-        targets_mask = np.pad(targets_mask, pad_width=((0, 0), (1, 1)), mode="constant", constant_values=0)
-        targets_mask = targets_mask.reshape(1, -1)
-        target_outputs.append(targets_mask)
-
-    # prepare output
-    region_mask_list = clip_regions["regions"].copy()
-    region_mask_list.extend(region_outputs)
-    target_mask_list = clip_regions["targets"].copy()
-    target_mask_list.extend(target_outputs)
-    weight_list = clip_regions["weights"].copy()
-    weight_list.extend([weight] * len(region_outputs))
-
-    clip_regions["regions"] = region_mask_list
-    clip_regions["targets"] = target_mask_list
-    clip_regions["weights"] = weight_list
-
-
-def create_masked_prompt(weighted_tokens, mask, mask_token):
-    mask_ids = list(zip(*np.nonzero(mask.reshape((len(weighted_tokens), -1))), strict=False))
-    new_prompt = copy.deepcopy(weighted_tokens)
-    for x, y in mask_ids:
-        new_prompt[x][y] = (mask_token,) + new_prompt[x][y][1:]
-    return new_prompt
-
-
-def process_cuts(encode, extra, tokens):
-    if not extra.get("cuts"):
-        return encode(tokens)
-
-    base = {
-        "base_tokens": tokens,
-        "regions": [],
-        "targets": [],
-        "weights": [],
-        "strict_mask": 1.0,
-        "start_from_masked": 1.0,
-        "mask_token": extra["tokenizer"].tokenizer("+")["input_ids"][1],
-    }
-
-    for cut in extra["cuts"]:
-        cutoff_add_region(base, extra["tokenizer"], *cut)
-
-    return encode_regions(base, encode, extra["tokenizer"])
-
-
-def debug_tokens(label, prompt, tokenizer):
-    log.debug("Tokens for %s", label)
-    for tokens in prompt:
-        tokens = (t for t in tokens if not torch.is_tensor(t[0]))
-        log.debug(" ".join(f"{x[0][0]} {x[1]}" for x in tokenizer.untokenize(tokens) if x[0][0] != tokenizer.end_token))
-
-
-def encode_regions(clip_regions, encode, tokenizer):
-    base_weighted_tokens = clip_regions["base_tokens"]
-    start_from_masked = clip_regions["start_from_masked"]
-    mask_token = clip_regions["mask_token"]
-    strict_mask = clip_regions["strict_mask"]
-
-    # calc base embedding
-    base_embedding_full, pool = encode(base_weighted_tokens)
-
-    # Avoid numpy value error and passthrough base embeddings if no regions are set.
-
-    # calc global target mask
-    global_target_mask = np.any(np.stack(clip_regions["targets"]), axis=0).astype(int)
-
-    # calc global region mask
-    global_region_mask = np.any(np.stack(clip_regions["regions"]), axis=0).astype(float)
-    regions_sum = np.sum(np.stack(clip_regions["regions"]), axis=0)
-    regions_normalized = np.divide(1, regions_sum, out=np.zeros_like(regions_sum), where=regions_sum != 0)
-
-    # mask base embeddings
-    base_masked_prompt = create_masked_prompt(base_weighted_tokens, global_target_mask, mask_token)
-    debug_tokens("base_masked", base_masked_prompt, tokenizer)
-    base_embedding_masked, _ = encode(base_masked_prompt)
-    base_embedding_start = base_embedding_full * (1 - start_from_masked) + base_embedding_masked * start_from_masked
-    base_embedding_outer = base_embedding_full * (1 - strict_mask) + base_embedding_masked * strict_mask
-
-    region_embeddings = []
-    for region, target, weight in zip(
-        clip_regions["regions"], clip_regions["targets"], clip_regions["weights"], strict=False
-    ):
-        region_masking = torch.tensor(
-            regions_normalized * region * weight, dtype=base_embedding_full.dtype, device=base_embedding_full.device
-        ).unsqueeze(-1)
-
-        region_prompt = create_masked_prompt(base_weighted_tokens, global_target_mask - target, mask_token)
-        debug_tokens("region", region_prompt, tokenizer)
-        region_emb, _ = encode(region_prompt)
-        region_emb -= base_embedding_start
-        # NegPiP support:
-        if region_emb.shape[1] == 2 * region_masking.shape[1]:
-            region_masking = torch.repeat_interleave(region_masking, 2, dim=1)
-        region_emb *= region_masking
-
-        region_embeddings.append(region_emb)
-    region_embeddings = torch.stack(region_embeddings).sum(dim=0)
-
-    embeddings_final_mask = torch.tensor(
-        global_region_mask, dtype=base_embedding_full.dtype, device=base_embedding_full.device
-    ).unsqueeze(-1)
-    # NegPiP support:
-    if region_embeddings.shape[1] == 2 * embeddings_final_mask.shape[1]:
-        embeddings_final_mask = torch.repeat_interleave(embeddings_final_mask, 2, dim=1)
-
-    embeddings_final = base_embedding_start * embeddings_final_mask + base_embedding_outer * (1 - embeddings_final_mask)
-    embeddings_final += region_embeddings
-    return embeddings_final, pool

prompt_control/cutoff_parser.py

@@ -1,25 +0,0 @@
-import re
-
-from .utils import parse_args
-
-CUTOFF_RE = re.compile(r"\[CUT:((.*?):(.*?))\]")
-
-
-def noop(x):
-    return x
-
-
-def parse_cuts(string):
-    text = CUTOFF_RE.sub(r"\2", string)
-    cutoffs = CUTOFF_RE.findall(string)
-    cs = []
-    for x, *_ in cutoffs:
-        p = x.split(":")
-        args = parse_args(
-            p, [(str, ""), (str, ""), (float, 0), (float, None), (float, None), (noop, None)], strip=False
-        )
-        args = tuple(args)
-        if not args[0] or not args[1] or (args[5] is not None and not args[5].strip()):
-            raise ValueError(f"Invalid CUT spec: [CUT:{x}]")
-        cs.append(args)
-    return text, cs

prompt_control/legacy/hijack.py

@@ -0,0 +1,160 @@
+from .utils import get_callback, unpatch_model
+import sys
+
+import logging
+import gc
+import comfy.model_management
+import os
+
+log = logging.getLogger("comfyui-prompt-control-legacy")
+
+
+def has_hijack(obj):
+    return hasattr(obj, "pc_hijack_done")
+
+
+def hijack(obj, attr, replacement):
+    setattr(obj, attr, replacement)
+    setattr(replacement, "pc_hijack_done", True)
+
+
+def hijack_sampler(module, function, is_custom):
+    mod = sys.modules[module]
+    orig_sampler = getattr(mod, function)
+    if has_hijack(orig_sampler):
+        return
+
+    from comfy.k_diffusion.sampling import BrownianTreeNoiseSampler
+
+    def pc_sample(*args, **kwargs):
+        model = args[0]
+        cb = get_callback(model)
+        BrownianTreeNoiseSampler.pc_reset(
+            model.model_options.get("pc_split_sampling"),
+            kwargs.get("force_full_denoise") or kwargs.get("denoise", 1.0) >= 1.0,
+        )
+        if cb:
+            try:
+                try:
+                    r = cb(orig_sampler, is_custom, *args, **kwargs)
+                except comfy.model_management.OOM_EXCEPTION:
+                    if not os.environ.get("PC_RETRY_ON_OOM"):
+                        raise
+                    log.error("Got OOM while sampling, freeing memory and retrying once...")
+                    unpatch_model(model)
+                    BrownianTreeNoiseSampler.pc_reset(False)
+                    gc.collect()
+                    comfy.model_management.soft_empty_cache()
+                    r = cb(orig_sampler, is_custom, *args, **kwargs)
+            except Exception:
+                log.error("Exception occurred during callback, unpatching model.")
+                unpatch_model(model)
+                BrownianTreeNoiseSampler.pc_reset(False)
+                raise
+        else:
+            r = orig_sampler(*args, **kwargs)
+        BrownianTreeNoiseSampler.pc_reset()
+        return r
+
+    hijack(mod, function, pc_sample)
+
+
+def hijack_ksampler(module, cls):
+    mod = sys.modules[module]
+    orig_sampler = getattr(mod, cls)
+    if has_hijack(orig_sampler):
+        return
+
+    class HijackedKSampler(orig_sampler):
+        def sample(
+            self,
+            noise,
+            positive,
+            negative,
+            cfg,
+            latent_image=None,
+            start_step=None,
+            last_step=None,
+            force_full_denoise=False,
+            denoise_mask=None,
+            sigmas=None,
+            callback=None,
+            disable_pbar=False,
+            seed=None,
+        ):
+            if sigmas is None:
+                sigmas = self.sigmas
+
+            from comfy.k_diffusion.sampling import BrownianTreeNoiseSampler
+
+            BrownianTreeNoiseSampler.set_global_sigmas(self.sigmas)
+
+            return super().sample(
+                noise,
+                positive,
+                negative,
+                cfg,
+                latent_image,
+                start_step,
+                last_step,
+                force_full_denoise,
+                denoise_mask,
+                sigmas,
+                callback,
+                disable_pbar,
+                seed,
+            )
+
+    hijack(mod, cls, HijackedKSampler)
+
+
+def hijack_browniannoisesampler(module, cls):
+    mod = sys.modules[module]
+    orig_sampler = getattr(mod, cls)
+    if has_hijack(orig_sampler):
+        return
+
+    class PCBrownianTreeNoiseSampler(orig_sampler):
+        global_instance = None
+        use_global_sigmas = False
+        global_sigmas = None
+        force_full_denoise = False
+
+        @classmethod
+        def pc_reset(cls, use_global_sigmas=False, force_full_denoise=False):
+            cls.global_instance = None
+            cls.global_sigmas = None
+            cls.use_global_sigmas = use_global_sigmas
+            cls.force_full_denoise = force_full_denoise
+
+        @classmethod
+        def set_global_sigmas(cls, sigmas):
+            if cls.global_sigmas is None and cls.use_global_sigmas:
+                cls.global_sigmas = (0 if cls.force_full_denoise else sigmas[sigmas > 0].min(), sigmas.max())
+                log.info(
+                    "Initializing BrownianTreeNoiseSampler instance with global sigmas %s, %s",
+                    cls.global_sigmas,
+                    cls.force_full_denoise,
+                )
+
+        def __init__(self, x, sigma_min, sigma_max, **kwargs):
+            if self.global_sigmas is not None:
+                sigma_min, sigma_max = self.global_sigmas
+            if not self.global_instance:
+                super().__init__(x, sigma_min, sigma_max, **kwargs)
+                PCBrownianTreeNoiseSampler.global_instance = self
+
+        def __call__(self, *args, **kwargs):
+            if self.global_instance and self != self.global_instance:
+                return self.global_instance(*args, **kwargs)
+            else:
+                return super().__call__(*args, **kwargs)
+
+    hijack(mod, cls, PCBrownianTreeNoiseSampler)
+
+
+def do_hijack():
+    hijack_browniannoisesampler("comfy.k_diffusion.sampling", "BrownianTreeNoiseSampler")
+    hijack_sampler("comfy.sample", "sample", False)
+    hijack_sampler("comfy.sample", "sample_custom", True)
+    hijack_ksampler("comfy.samplers", "KSampler")

prompt_control/legacy/node_aio.py

@@ -0,0 +1,49 @@
+from .node_clip import control_to_clip_common
+from .node_lora import schedule_lora_common
+from ..parser import parse_prompt_schedules
+
+
+class PromptControlSimple:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "model": ("MODEL",),
+                "clip": ("CLIP",),
+                "positive": ("STRING", {"multiline": True}),
+                "negative": ("STRING", {"multiline": True}),
+            },
+            "optional": {
+                "tags": ("STRING", {"default": ""}),
+                "start": ("FLOAT", {"min": 0.0, "max": 1.0, "step": 0.1, "default": 0.0}),
+                "end": ("FLOAT", {"min": 0.0, "max": 1.0, "step": 0.1, "default": 1.0}),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("MODEL", "CONDITIONING", "CONDITIONING", "MODEL", "CONDITIONING", "CONDITIONING")
+    RETURN_NAMES = ("model", "positive", "negative", "model_filtered", "pos_filtered", "neg_filtered")
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, model, clip, positive, negative, tags="", start=0.0, end=1.0):
+        lora_cache = {}
+        cond_cache = {}
+        pos_sched = parse_prompt_schedules(positive)
+        pos_cond = pos_filtered = control_to_clip_common(clip, pos_sched, lora_cache, cond_cache)
+
+        neg_sched = parse_prompt_schedules(negative)
+        neg_cond = neg_filtered = control_to_clip_common(clip, neg_sched, lora_cache, cond_cache)
+
+        new_model = model_filtered = schedule_lora_common(model, pos_sched, lora_cache)
+
+        if [tags.strip(), start, end] != ["", 0.0, 1.0]:
+            pos_filtered = control_to_clip_common(
+                clip, pos_sched.with_filters(tags, start, end), lora_cache, cond_cache
+            )
+            neg_filtered = control_to_clip_common(
+                clip, neg_sched.with_filters(tags, start, end), lora_cache, cond_cache
+            )
+            model_filtered = schedule_lora_common(model, pos_sched.with_filters(tags, start, end), lora_cache)
+
+        return (new_model, pos_cond, neg_cond, model_filtered, pos_filtered, neg_filtered)

prompt_control/legacy/node_clip.py

@@ -0,0 +1,703 @@
+import logging
+import re
+import torch
+from ..parser import parse_prompt_schedules, parse_cuts
+from .utils import Timer, equalize, apply_loras_from_spec
+from ..utils import safe_float, get_function, parse_floats  # non-legacy
+from .perp_weight import perp_encode
+from comfy_extras.nodes_mask import FeatherMask, MaskComposite
+from node_helpers import conditioning_set_values
+
+
+log = logging.getLogger("comfyui-prompt-control-legacy")
+
+try:
+    from custom_nodes.ComfyUI_ADV_CLIP_emb.adv_encode import (
+        advanced_encode_from_tokens,
+        encode_token_weights_l,
+        encode_token_weights_g,
+        prepareXL,
+        encode_token_weights,
+    )
+
+    have_advanced_encode = True
+    AVAILABLE_STYLES = ["comfy", "A1111", "compel", "comfy++", "down_weight"]
+    AVAILABLE_NORMALIZATIONS = ["none", "mean", "length", "length+mean"]
+except ImportError:
+    have_advanced_encode = False
+    AVAILABLE_STYLES = ["comfy"]
+    AVAILABLE_NORMALIZATIONS = ["none"]
+
+try:
+    from custom_nodes.Vector_Sculptor_ComfyUI.nodes import vector_sculptor_tokens
+
+    can_sculpt = True
+    log.info("Vector sculptor extension detected, can use SCULPT()")
+except ImportError:
+    can_sculpt = False
+
+
+AVAILABLE_STYLES.append("perp")
+log.info("Use STYLE(weight_interpretation, normalization) at the start of a prompt to use advanced encodings")
+log.info("Weight interpretations available: %s", ",".join(AVAILABLE_STYLES))
+log.info("Normalization types available: %s", ",".join(AVAILABLE_NORMALIZATIONS))
+
+
+def linear_interpolate_cond(
+    start, end, from_step=0.0, to_step=1.0, step=0.1, start_at=None, end_at=None, prompt_start="N/A", prompt_end="N/A"
+):
+    count = min(len(start), len(end))
+    if len(start) != len(end):
+        log.info(
+            "Length of conds to interpolate does not match (start=%s != end=%s), interpolating up to %s.",
+            len(start),
+            len(end),
+            count,
+        )
+
+    all_res = []
+    for idx in range(count):
+        res = []
+        from_cond, to_cond = equalize(start[idx][0], end[idx][0])
+        from_pooled = start[idx][1].get("pooled_output")
+        to_pooled = end[idx][1].get("pooled_output")
+        start_at = start_at if start_at is not None else from_step
+        end_at = end_at if end_at is not None else to_step
+        total_steps = int(round((to_step - from_step) / step, 0))
+        num_steps = int(round((end_at - from_step) / step, 0))
+        start_on = int(round((start_at - from_step) / step, 0))
+        start_pct = start_at
+        log.debug(
+            f"interpolate_cond {idx=} {from_step=} {to_step=} {start_at=} {end_at=} {total_steps=} {num_steps=} {start_on=} {step=}"
+        )
+        x = 1 / (total_steps + 1)
+        for s in range(start_on, num_steps):
+            factor = round((s + 1) * x, 2)
+            new_cond = from_cond + (to_cond - from_cond) * factor
+            if from_pooled is not None and to_pooled is not None:
+                from_pooled, to_pooled = equalize(from_pooled, to_pooled)
+                new_pooled = from_pooled + (to_pooled - from_pooled) * factor
+            elif from_pooled is not None:
+                new_pooled = from_pooled
+
+            n = [new_cond, start[idx][1].copy()]
+            if new_pooled is not None:
+                n[1]["pooled_output"] = new_pooled
+            n[1]["start_percent"] = round(start_pct, 2)
+            n[1]["end_percent"] = min(round((start_pct + step), 2), 1.0)
+            start_pct += step
+            start_pct = round(start_pct, 2)
+            if prompt_start:
+                n[1]["prompt"] = f"linear:{round(1.0 - factor, 2)} / {factor}"
+            log.debug(
+                "Interpolating at step %s with factor %s (%s, %s)...",
+                s,
+                factor,
+                n[1]["start_percent"],
+                n[1]["end_percent"],
+            )
+            res.append(n)
+        if res:
+            res[-1][1]["end_percent"] = round(end_at, 2)
+            all_res.extend(res)
+    return all_res
+
+
+def get_control_points(schedule, steps, encoder):
+    assert len(steps) > 1
+    new_steps = set(steps)
+
+    for step in (s[0] for s in schedule if s[0] >= steps[0] and s[0] <= steps[-1]):
+        new_steps.add(step)
+    control_points = [(s, encoder(schedule.at_step(s)[1])) for s in new_steps]
+    log.debug("Actual control points for interpolation: %s (from %s)", new_steps, steps)
+    return sorted(control_points, key=lambda x: x[0])
+
+
+def linear_interpolator(control_points, step, start_pct, end_pct):
+    o_start, start = control_points[0]
+    o_end, _ = control_points[-1]
+    t_start = o_start
+    conds = []
+    for t_end, end in control_points[1:]:
+        if t_start < start_pct:
+            t_start, start = t_end, end
+            continue
+        if t_start >= end_pct:
+            break
+        cs = linear_interpolate_cond(start, end, o_start, o_end, step, start_at=t_start, end_at=end_pct)
+        if cs:
+            conds.extend(cs)
+        else:
+            break
+        t_start = t_end
+        start = end
+    return conds
+
+
+class ScheduleToCond:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {"clip": ("CLIP",), "prompt_schedule": ("PROMPT_SCHEDULE",)},
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("CONDITIONING",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, clip, prompt_schedule):
+        with Timer("ScheduleToCond"):
+            r = (control_to_clip_common(clip, prompt_schedule),)
+        return r
+
+
+class EditableCLIPEncode:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "clip": ("CLIP",),
+                "text": ("STRING", {"multiline": True}),
+            },
+            "optional": {"filter_tags": ("STRING", {"default": ""})},
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("CONDITIONING",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "parse"
+
+    def parse(self, clip, text, filter_tags=""):
+        parsed = parse_prompt_schedules(text).with_filters(filter_tags)
+        return (control_to_clip_common(clip, parsed),)
+
+
+def get_sdxl(text, defaults):
+    # Defaults fail to parse and get looked up from the defaults dict
+    text, sdxl = get_function(text, "SDXL", ["none", "none", "none"])
+    if not sdxl:
+        return text, {}
+    args = sdxl[0]
+    d = defaults
+    w, h = parse_floats(args[0], [d.get("sdxl_width", 1024), d.get("sdxl_height", 1024)], split_re="\\s+")
+    tw, th = parse_floats(args[1], [d.get("sdxl_twidth", 1024), d.get("sdxl_theight", 1024)], split_re="\\s+")
+    cropw, croph = parse_floats(args[2], [d.get("sdxl_cwidth", 0), d.get("sdxl_cheight", 0)], split_re="\\s+")
+
+    opts = {
+        "width": int(w),
+        "height": int(h),
+        "target_width": int(tw),
+        "target_height": int(th),
+        "crop_w": int(cropw),
+        "crop_h": int(croph),
+    }
+    return text, opts
+
+
+def get_style(text, default_style="comfy", default_normalization="none"):
+    text, styles = get_function(text, "STYLE", [default_style, default_normalization])
+    if not styles:
+        return default_style, default_normalization, text
+    style, normalization = styles[0]
+    style = style.strip()
+    normalization = normalization.strip()
+    if style not in AVAILABLE_STYLES:
+        log.warning("Unrecognized prompt style: %s. Using %s", style, default_style)
+        style = default_style
+
+    if normalization not in AVAILABLE_NORMALIZATIONS:
+        log.warning("Unrecognized prompt normalization: %s. Using %s", normalization, default_normalization)
+        normalization = default_normalization
+
+    return style, normalization, text
+
+
+def encode_regions(clip, tokens, regions, weight_interpretation="comfy", token_normalization="none"):
+    from custom_nodes.ComfyUI_Cutoff.cutoff import CLIPSetRegion, finalize_clip_regions
+
+    clip_regions = {
+        "clip": clip,
+        "base_tokens": tokens,
+        "regions": [],
+        "targets": [],
+        "weights": [],
+    }
+
+    strict_mask = 1.0
+    start_from_masked = 1.0
+    mask_token = ""
+
+    for region in regions:
+        region_text, target_text, w, sm, sfm, mt = region
+        if w is not None:
+            w = safe_float(w, 0)
+        else:
+            w = 1.0
+        if sm is not None:
+            strict_mask = safe_float(sm, 1.0)
+        if sfm is not None:
+            start_from_masked = safe_float(sfm, 1.0)
+        if mt is not None:
+            mask_token = mt
+        log.info("Region: text %s, target %s, weight %s", region_text.strip(), target_text.strip(), w)
+        (clip_regions,) = CLIPSetRegion.add_clip_region(None, clip_regions, region_text, target_text, w)
+    log.info("Regions: mask_token=%s strict_mask=%s start_from_masked=%s", mask_token, strict_mask, start_from_masked)
+
+    (r,) = finalize_clip_regions(
+        clip_regions, mask_token, strict_mask, start_from_masked, token_normalization, weight_interpretation
+    )
+    cond, pooled = r[0][0], r[0][1].get("pooled_output")
+    return cond, pooled
+
+
+SHUFFLE_GEN = torch.Generator(device="cpu")
+
+
+def shuffle_chunk(shuffle, c):
+    func, shuffle = shuffle
+    shuffle_count = int(safe_float(shuffle[0], 0))
+    _, separator, joiner = shuffle
+    if separator == "default":
+        separator = ","
+
+    if not separator:
+        separator = ","
+
+    joiner = {
+        "default": ",",
+        "separator": separator,
+    }.get(joiner, joiner)
+
+    log.info("%s arg=%s sep=%s join=%s", func, shuffle_count, separator, joiner)
+    separated = c.split(separator)
+    if func == "SHIFT":
+        shuffle_count = shuffle_count % len(separated)
+        permutation = separated[shuffle_count:] + separated[:shuffle_count]
+    elif func == "SHUFFLE":
+        SHUFFLE_GEN.manual_seed(shuffle_count)
+        permutation = [separated[i] for i in torch.randperm(len(separated), generator=SHUFFLE_GEN)]
+    else:
+        # ??? should never get here
+        permutation = separated
+
+    permutation = [p for p in permutation if p.strip()]
+    if permutation != separated:
+        c = joiner.join(permutation)
+    return c
+
+
+def fix_word_ids(tokens):
+    """Fix word indexes. Tokenizing separately (when BREAKs exist) causes the indexes to restart which causes problems with some weighting algorithms that rely on them"""
+    for key in tokens:
+        max_idx = 0
+        for group in range(len(tokens[key])):
+            for i, token in enumerate(tokens[key][group]):
+                if len(token) < 3:
+                    # No need to fix ids when they don't exist
+                    return tokens
+                # Ignore zeros, they represent the padding token
+                if token[2] != 0 and token[2] < max_idx:
+                    tokens[key][group][i] = (token[0], token[1], token[2] + max_idx)
+            max_idx = max(max_idx, max(x for _, _, x in tokens[key][group]))
+    return tokens
+
+
+def encode_prompt(clip, text, default_style="comfy", default_normalization="none"):
+    style, normalization, text = get_style(text, default_style, default_normalization)
+    sculpts = []
+    if can_sculpt:
+        text, sculpts = get_function(text, "SCULPT", ["1.0", "forward", "none"])
+    text, regions = parse_cuts(text)
+    # defaults=None means there is no argument parsing at all
+    text, l_prompts = get_function(text, "CLIP_L", defaults=None)
+    chunks = re.split(r"\bBREAK\b", text)
+    token_chunks = []
+    need_word_ids = len(regions) > 0 or (have_advanced_encode and style != "perp")
+    for c in chunks:
+        c, shuffles = get_function(c.strip(), "(SHIFT|SHUFFLE)", ["0", "default", "default"], return_func_name=True)
+        r = c
+        for s in shuffles:
+            r = shuffle_chunk(s, r)
+        if r != c:
+            log.info("Shuffled prompt chunk to %s", r)
+            c = r
+        if sculpts:
+            w, method, norm = sculpts[0]
+            log.info("Using vector sculptor with method=%s norm=%s w=%s", method, norm, w)
+            w = safe_float(w, 1.0)
+            t = vector_sculptor_tokens(clip, c, method, norm, w)
+        else:
+            # Tokenizer returns padded results
+            t = clip.tokenize(c, return_word_ids=need_word_ids)
+        token_chunks.append(t)
+    tokens = token_chunks[0]
+
+    for key in tokens:
+        for c in token_chunks[1:]:
+            tokens[key].extend(c[key])
+
+    # Non-SDXL has only "l"
+    if "g" in tokens and l_prompts:
+        text_l = " ".join(l_prompts)
+        log.info("Encoded SDXL CLIP_L prompt: %s", text_l)
+        tokens["l"] = clip.tokenize(text_l, return_word_ids=need_word_ids)["l"]
+
+    if "g" in tokens and "l" in tokens and len(tokens["l"]) != len(tokens["g"]):
+        empty = clip.tokenize("", return_word_ids=need_word_ids)
+        while len(tokens["l"]) < len(tokens["g"]):
+            tokens["l"] += empty["l"]
+        while len(tokens["l"]) > len(tokens["g"]):
+            tokens["g"] += empty["g"]
+
+    tokens = fix_word_ids(tokens)
+
+    if len(regions) > 0:
+        return encode_regions(clip, tokens, regions, style, normalization)
+
+    if style == "perp":
+        if normalization != "none":
+            log.warning("Normalization is not supported with perp style weighting. Ignored '%s'", normalization)
+        return perp_encode(clip, tokens)
+
+    if "t5xxl" not in tokens and have_advanced_encode and not sculpts:
+        if "g" in tokens:
+            embs_l = None
+            embs_g = None
+            pooled = None
+            if "l" in tokens:
+                embs_l, _ = advanced_encode_from_tokens(
+                    tokens["l"],
+                    normalization,
+                    style,
+                    lambda x: encode_token_weights(clip, x, encode_token_weights_l),
+                    return_pooled=False,
+                )
+            if "g" in tokens:
+                embs_g, pooled = advanced_encode_from_tokens(
+                    tokens["g"],
+                    normalization,
+                    style,
+                    lambda x: encode_token_weights(clip, x, encode_token_weights_g),
+                    return_pooled=True,
+                    apply_to_pooled=False,
+                )
+            # Hardcoded clip_balance
+            return prepareXL(embs_l, embs_g, pooled, 0.5)
+        return advanced_encode_from_tokens(
+            tokens["l"],
+            normalization,
+            style,
+            lambda x: clip.encode_from_tokens({"l": x}, return_pooled=True),
+            return_pooled=True,
+            apply_to_pooled=True,
+        )
+    else:
+        return clip.encode_from_tokens(tokens, return_pooled=True)
+
+
+def get_area(text):
+    text, areas = get_function(text, "AREA", ["0 1", "0 1", "1"])
+    if not areas:
+        return text, None
+
+    args = areas[0]
+    x, w = parse_floats(args[0], [0.0, 1.0], split_re="\\s+")
+    y, h = parse_floats(args[1], [0.0, 1.0], split_re="\\s+")
+    weight = safe_float(args[2], 1.0)
+
+    def is_pct(f):
+        return f >= 0.0 and f <= 1.0
+
+    def is_pixel(f):
+        return f == 0 or f > 1
+
+    if all(is_pct(v) for v in [h, w, y, x]):
+        area = ("percentage", h, w, y, x)
+    elif all(is_pixel(v) for v in [h, w, y, x]):
+        area = (int(h) // 8, int(w) // 8, int(y) // 8, int(x) // 8)
+    else:
+        raise Exception(
+            f"AREA specified with invalid size {x} {w}, {h} {y}. They must either all be percentages between 0 and 1 or positive integer pixel values excluding 1"
+        )
+
+    return text, (area, weight)
+
+
+def get_mask_size(text, defaults):
+    text, sizes = get_function(text, "MASK_SIZE", ["512", "512"])
+    if not sizes:
+        return text, (defaults.get("mask_width", 512), defaults.get("mask_height", 512))
+    w, h = sizes[0]
+    return text, (int(w), int(h))
+
+
+def make_mask(args, size, weight):
+    x1, x2 = parse_floats(args[0], [0.0, 1.0], split_re="\\s+")
+    y1, y2 = parse_floats(args[1], [0.0, 1.0], split_re="\\s+")
+
+    def is_pct(f):
+        return f >= 0.0 and f <= 1.0
+
+    def is_pixel(f):
+        return f == 0 or f > 1
+
+    if all(is_pct(v) for v in [x1, x2, y1, y2]):
+        w, h = size
+        xs = int(w * x1), int(w * x2)
+        ys = int(h * y1), int(h * y2)
+    elif all(is_pixel(v) for v in [x1, x2, y1, y2]):
+        w, h = size
+        xs = int(x1), int(x2)
+        ys = int(y1), int(y2)
+    else:
+        raise Exception(
+            f"MASK specified with invalid size {x1} {x2}, {y1} {y2}. They must either all be percentages between 0 and 1 or positive integer pixel values excluding 1"
+        )
+
+    mask = torch.full((h, w), 0, dtype=torch.float32, device="cpu")
+    mask[ys[0] : ys[1], xs[0] : xs[1]] = weight
+    mask = mask.unsqueeze(0)
+    log.info("Mask xs=%s, ys=%s, shape=%s, weight=%s", xs, ys, mask.shape, weight)
+    return mask
+
+
+def get_mask(text, size, input_masks):
+    """Parse MASK(x1 x2, y1 y2, weight), IMASK(i, weight) and FEATHER(left top right bottom)"""
+    # TODO: combine multiple masks
+    text, masks = get_function(text, "MASK", ["0 1", "0 1", "1", "multiply"])
+    text, imasks = get_function(text, "IMASK", ["0", "1", "multiply"])
+    text, feathers = get_function(text, "FEATHER", ["0 0 0 0"])
+    text, maskw = get_function(text, "MASKW", ["1.0"])
+    if not masks and not imasks:
+        return text, None, None
+
+    def feather(f, mask):
+        l, t, r, b, *_ = [int(x) for x in parse_floats(f[0], [0, 0, 0, 0], split_re="\\s+")]
+        mask = FeatherMask().feather(mask, l, t, r, b)[0]
+        log.info("FeatherMask l=%s, t=%s, r=%s, b=%s", l, t, r, b)
+        return mask
+
+    mask = None
+    totalweight = 1.0
+    if maskw:
+        totalweight = safe_float(maskw[0][0], 1.0)
+    i = 0
+    for m in masks:
+        weight = safe_float(m[2], 1.0)
+        op = m[3]
+        nextmask = make_mask(m, size, weight)
+        if i < len(feathers):
+            nextmask = feather(feathers[i], nextmask)
+        i += 1
+        if mask is not None:
+            log.info("MaskComposite op=%s", op)
+            mask = MaskComposite().combine(mask, nextmask, 0, 0, op)[0]
+        else:
+            mask = nextmask
+
+    for idx, w, op in imasks:
+        idx = int(safe_float(idx, 0.0))
+        w = safe_float(w, 1.0)
+        if len(input_masks) < idx + 1:
+            log.warn("IMASK index %s not found, ignoring...", idx)
+            continue
+        nextmask = input_masks[idx] * w
+        if i < len(feathers):
+            nextmask = feather(feathers[i], nextmask)
+        i += 1
+        if mask is not None:
+            mask = MaskComposite().combine(mask, nextmask, 0, 0, op)[0]
+        else:
+            mask = nextmask
+
+    # apply leftover FEATHER() specs to the whole
+    for f in feathers[i:]:
+        mask = feather(f, mask)
+
+    return text, mask, totalweight
+
+
+def get_noise(text):
+    text, noises = get_function(
+        text,
+        "NOISE",
+        ["0.0", "none"],
+    )
+    if not noises:
+        return text, None, None
+    w = 0
+    # Only take seed from first noise spec, for simplicity
+    seed = safe_float(noises[0][1], "none")
+    if seed == "none":
+        gen = None
+    else:
+        gen = torch.Generator()
+        gen.manual_seed(int(seed))
+    for n in noises:
+        w += safe_float(n[0], 0.0)
+    return text, max(min(w, 1.0), 0.0), gen
+
+
+def apply_noise(cond, weight, gen):
+    if cond is None or not weight:
+        return cond
+
+    n = torch.randn(cond.size(), generator=gen).to(cond)
+
+    return cond * (1 - weight) + n * weight
+
+
+def do_encode(clip, text, defaults, masks):
+    # First style modifier applies to ANDed prompts too unless overridden
+    style, normalization, text = get_style(text)
+    text, mask_size = get_mask_size(text, defaults)
+
+    # Don't sum ANDs if this is in prompt
+    alt_method = "COMFYAND()" in text
+    text = text.replace("COMFYAND()", "")
+
+    prompts = [p.strip() for p in re.split(r"\bAND\b", text)]
+
+    p, sdxl_opts = get_sdxl(prompts[0], defaults)
+    prompts[0] = p
+
+    def weight(t):
+        opts = {}
+        m = re.search(r":(-?\d\.?\d*)(![A-Za-z]+)?$", t)
+        if not m:
+            return (1.0, opts, t)
+        w = float(m[1])
+        tag = m[2]
+        t = t[: m.span()[0]]
+        if tag == "!noscale":
+            opts["scale"] = 1
+
+        return w, opts, t
+
+    conds = []
+    res = []
+    scale = sum(abs(weight(p)[0]) for p in prompts if not ("AREA(" in p or "MASK(" in p))
+    for prompt in prompts:
+        prompt, mask, mask_weight = get_mask(prompt, mask_size, masks)
+        w, opts, prompt = weight(prompt)
+        text, noise_w, generator = get_noise(text)
+        if not w:
+            continue
+        prompt, area = get_area(prompt)
+        prompt, local_sdxl_opts = get_sdxl(prompt, defaults)
+        cond, pooled = encode_prompt(clip, prompt, style, normalization)
+        cond = apply_noise(cond, noise_w, generator)
+        pooled = apply_noise(pooled, noise_w, generator)
+
+        settings = {"prompt": prompt}
+        if alt_method:
+            settings["strength"] = w
+        settings.update(sdxl_opts)
+        settings.update(local_sdxl_opts)
+        if area:
+            settings["area"] = area[0]
+            settings["strength"] = area[1]
+            settings["set_area_to_bounds"] = False
+        if mask is not None:
+            settings["mask"] = mask
+            settings["mask_strength"] = mask_weight
+
+        if mask is not None or area or alt_method or local_sdxl_opts:
+            if pooled is not None:
+                settings["pooled_output"] = pooled
+            conds.append([cond, settings])
+        else:
+            s = opts.get("scale", scale)
+            res.append((cond, pooled, w / s))
+
+    sumconds = [r[0] * r[2] for r in res]
+    pooleds = [r[1] for r in res if r[1] is not None]
+
+    if len(res) > 0:
+        opts = sdxl_opts
+        if pooleds:
+            opts["pooled_output"] = sum(equalize(*pooleds))
+        sumcond = sum(equalize(*sumconds))
+        conds.append([sumcond, opts])
+    return conds
+
+
+def debug_conds(conds):
+    r = []
+    for i, c in enumerate(conds):
+        x = c[1].copy()
+        if "pooled_output" in x:
+            del x["pooled_output"]
+        r.append((i, x))
+    return r
+
+
+def control_to_clip_common(clip, schedules, lora_cache=None, cond_cache=None):
+    orig_clip = clip.clone()
+    current_loras = {}
+    if lora_cache is None:
+        lora_cache = {}
+    start_pct = 0.0
+    conds = []
+    cond_cache = cond_cache if cond_cache is not None else {}
+
+    def c_str(c):
+        r = [c["prompt"]]
+        loras = c["loras"]
+        for k in sorted(loras.keys()):
+            r.append(k)
+            r.append(loras[k]["weight_clip"])
+            for lbw, val in loras[k].get("lbw", {}).items():
+                r.append(lbw)
+                r.append(val)
+        return "".join(str(i) for i in r)
+
+    def encode(c):
+        nonlocal clip
+        nonlocal current_loras
+        prompt = c["prompt"]
+        loras = c["loras"]
+        cachekey = c_str(c)
+        cond = cond_cache.get(cachekey)
+        if cond is None:
+            if loras != current_loras:
+                _, clip = apply_loras_from_spec(loras, clip=orig_clip, cache=lora_cache, applied_loras=current_loras)
+                current_loras = loras
+            cond_cache[cachekey] = do_encode(clip, prompt, schedules.defaults, schedules.masks)
+        return cond_cache[cachekey]
+
+    for end_pct, c in schedules:
+        interpolations = [
+            i
+            for i in schedules.interpolations
+            if (start_pct >= i[0][0] and start_pct < i[0][-1]) or (end_pct > i[0][0] and start_pct < i[0][-1])
+        ]
+        new_start_pct = start_pct
+        if interpolations:
+            min_step = min(i[1] for i in interpolations)
+            for i in interpolations:
+                control_points, _ = i
+                interpolation_end_pct = min(control_points[-1], end_pct)
+                interpolation_start_pct = max(control_points[0], start_pct)
+
+                control_points = get_control_points(schedules, control_points, encode)
+                cs = linear_interpolator(control_points, min_step, interpolation_start_pct, interpolation_end_pct)
+                conds.extend(cs)
+                new_start_pct = max(new_start_pct, interpolation_end_pct)
+        start_pct = new_start_pct
+
+        if start_pct < end_pct:
+            cond = encode(c)
+            # Node functions return lists of cond
+            cond = conditioning_set_values(
+                cond, {"start_percent": round(start_pct, 2), "end_percent": round(end_pct, 2), "prompt": c["prompt"]}
+            )
+            conds.extend(cond)
+
+        start_pct = end_pct
+        log.debug("Conds at the end: %s", debug_conds(conds))
+
+    log.debug("Final cond info: %s", debug_conds(conds))
+    return conds

prompt_control/legacy/node_lora.py

@@ -0,0 +1,251 @@
+import logging
+import torch
+
+from .utils import unpatch_model, clone_model, set_callback, apply_loras_from_spec
+from ..parser import parse_prompt_schedules
+from .hijack import do_hijack
+from comfy.samplers import CFGGuider
+
+log = logging.getLogger("comfyui-prompt-control-legacy")
+
+
+def apply_lora_for_step(schedules, step, total_steps, state, original_model, lora_cache, patch=True):
+    # zero-indexed steps, 0 = first step, but schedules are 1-indexed
+    sched = schedules.at_step(step + 1, total_steps)
+    lora_spec = sched[1]["loras"]
+
+    if state["applied_loras"] != lora_spec:
+        log.debug("At step %s, applying lora_spec %s", step, lora_spec)
+        m, _ = apply_loras_from_spec(
+            lora_spec,
+            model=state["model"],
+            orig_model=original_model,
+            cache=lora_cache,
+            patch=patch,
+            applied_loras=state["applied_loras"],
+        )
+        state["model"] = m
+        state["applied_loras"] = lora_spec
+
+
+def schedule_lora_common(model, schedules, lora_cache=None):
+    do_hijack()
+    orig_model = clone_model(model)
+    orig_model.model_options["pc_schedules"] = schedules
+
+    if lora_cache is None:
+        lora_cache = {}
+
+    def sampler_cb(orig_sampler, is_custom, *args, **kwargs):
+        split_sampling = args[0].model_options.get("pc_split_sampling")
+        state = {}
+        if is_custom:
+            steps = len(args[4])
+            log.info(
+                "SamplerCustom detected, number of steps not available. LoRA schedules will be calculated based on the number of sigmas (%s)",
+                steps,
+            )
+        else:
+            log.debug("Normal sampler detected, using steps from parameter")
+            steps = args[2]
+        start_step = kwargs.get("start_step") or 0
+        # The model patcher may change if LoRAs are applied
+        state["model"] = args[0]
+        state["applied_loras"] = {}
+
+        orig_cb = kwargs["callback"]
+
+        def step_callback(*args, **kwargs):
+            current_step = args[0] + start_step
+            apply_lora_for_step(schedules, current_step, steps, state, orig_model, lora_cache, patch=True)
+            if orig_cb:
+                return orig_cb(*args, **kwargs)
+
+        kwargs["callback"] = step_callback
+
+        apply_lora_for_step(schedules, start_step, steps, state, orig_model, lora_cache, patch=True)
+
+        def filter_conds(conds, t, start_t, end_t):
+            r = []
+            for c in conds:
+                x = c[1].copy()
+                start_at = round(x["start_percent"], 2)
+                end_at = round(x["end_percent"], 2)
+                # Take any cond that has any effect before end_t, since the percentages may not perfectly match
+                if end_t > start_at and end_t <= end_at:
+                    del x["start_percent"]
+                    del x["end_percent"]
+                    r.append([c[0].clone(), x])
+                else:
+                    log.debug("Rejecting cond (%s, %s) between (%s, %s)", start_at, end_at, start_t, end_t)
+            if len(r) == 0:
+                log.error("No %s conds between (%s, %s); Try adjusting your steps", t, start_t, end_t)
+            return r
+
+        def get_steps(conds):
+            for c in conds:
+                yield round(c[1].get("end_percent", 0), 2)
+
+        if split_sampling:
+            actual_end_step = kwargs["last_step"] or steps
+            first_step = True
+            s = args[8]
+            all_steps = sorted(set(int(steps * i) for i in [1.0] + list(get_steps(args[6])) + list(get_steps(args[7]))))
+            for end_step in all_steps:
+                if end_step <= start_step:
+                    continue
+                start_t = round(start_step / steps, 2)
+                end_t = round(end_step / steps, 2)
+                new_kwargs = kwargs.copy()
+                new_args = list(args)
+                new_args[0] = state["model"]
+                new_args[6] = filter_conds(new_args[6], "positive", start_t, end_t)
+                new_args[7] = filter_conds(new_args[7], "negative", start_t, end_t)
+                new_args[8] = s
+                log.info("Sampling from %s to %s (total: %s)", start_step, end_step, actual_end_step)
+                new_kwargs["start_step"] = start_step
+                new_kwargs["last_step"] = end_step
+                if end_step >= min(steps, actual_end_step):
+                    new_kwargs["force_full_denoise"] = kwargs["force_full_denoise"]
+                else:
+                    new_kwargs["force_full_denoise"] = False
+
+                if not first_step:
+                    # disable_noise apparently does nothing currently, we need to override noise in args
+                    new_kwargs["disable_noise"] = True
+                    new_args[1] = torch.zeros_like(s)
+
+                s = orig_sampler(*new_args, **new_kwargs)
+                start_step = end_step
+                first_step = False
+        else:
+            args = list(args)
+            args[0] = state["model"]
+            s = orig_sampler(*args, **kwargs)
+
+        unpatch_model(state["model"])
+
+        return s
+
+    set_callback(orig_model, sampler_cb)
+
+    return orig_model
+
+
+class PCWrapGuider:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "guider": ("GUIDER",),
+            },
+        }
+
+    DEPRECATED = True
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+    RETURN_TYPES = ("GUIDER",)
+
+    def apply(self, guider):
+        return (PCGuider(guider),)
+
+
+class PCGuider(CFGGuider):
+    def __init__(self, original_guider):
+        if "pc_schedules" not in original_guider.model_patcher.model_options:
+            raise ValueError(
+                "The guider passed to PCWrapGuider must contain a Model that has schedules applied. Use ScheduleToModel"
+            )
+        self.schedules = original_guider.model_patcher.model_options["pc_schedules"]
+        self.guider = original_guider
+        self.lora_cache = {}
+        # sets self.model_patcher
+        super().__init__(original_guider.model_patcher)
+
+    def sample(self, *args, **kwargs):
+        orig_cb = kwargs["callback"]
+        sigmas = args[3]
+        state = {"model": self.guider.model_patcher, "applied_loras": {}}
+
+        def step_callback(*args, **kwargs):
+            apply_lora_for_step(
+                self.schedules,
+                args[0],
+                len(sigmas),
+                state,
+                self.guider.model_patcher,
+                self.lora_cache,
+                patch=True,
+            )
+            if orig_cb:
+                return orig_cb(*args, **kwargs)
+
+        kwargs["callback"] = step_callback
+        apply_lora_for_step(
+            self.schedules, 0, len(sigmas), state, self.guider.model_patcher, self.lora_cache, patch=True
+        )
+        try:
+            r = self.guider.sample(*args, **kwargs)
+        finally:
+            unpatch_model(state["model"])
+        return r
+
+
+class ScheduleToModel:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "model": ("MODEL",),
+                "prompt_schedule": ("PROMPT_SCHEDULE",),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("MODEL",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, model, prompt_schedule):
+        return (schedule_lora_common(model, prompt_schedule),)
+
+
+class PCSplitSampling:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "model": ("MODEL",),
+                "split_sampling": (["enable", "disable"],),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("MODEL",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, model, split_sampling):
+        model = clone_model(model)
+        model.model_options["pc_split_sampling"] = split_sampling == "enable"
+        return (model,)
+
+
+class LoRAScheduler:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "model": ("MODEL",),
+                "text": ("STRING", {"multiline": True}),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("MODEL",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, model, text):
+        schedules = parse_prompt_schedules(text)
+        return (schedule_lora_common(model, schedules),)

prompt_control/legacy/node_other.py

@@ -0,0 +1,159 @@
+import logging
+from ..parser import parse_prompt_schedules
+
+log = logging.getLogger("comfyui-prompt-control-legacy")
+
+
+class FilterSchedule:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {"prompt_schedule": ("PROMPT_SCHEDULE",)},
+            "optional": {
+                "tags": ("STRING", {"default": ""}),
+                "start": ("FLOAT", {"min": 0.00, "max": 1.00, "default": 0.0, "step": 0.01}),
+                "end": ("FLOAT", {"min": 0.00, "max": 1.00, "default": 1.0, "step": 0.01}),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("PROMPT_SCHEDULE",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, prompt_schedule, tags="", start=0.0, end=1.0):
+        p = prompt_schedule.with_filters(tags, start=start, end=end)
+        log.debug(
+            f"Filtered {prompt_schedule.parsed_prompt} with: ({tags}, {start}, {end}); the result is %s",
+            p.parsed_prompt,
+        )
+        return (p,)
+
+
+class PCApplySettings:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"prompt_schedule": ("PROMPT_SCHEDULE",), "settings": ("SCHEDULE_SETTINGS",)}}
+
+    DEPRECATED = True
+    RETURN_TYPES = ("PROMPT_SCHEDULE",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, prompt_schedule, settings):
+        return (prompt_schedule.with_filters(defaults=settings),)
+
+
+class PCScheduleAddMasks:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {"prompt_schedule": ("PROMPT_SCHEDULE",)},
+            "optional": {
+                "mask1": ("MASK",),
+                "mask2": ("MASK",),
+                "mask3": ("MASK",),
+                "mask4": ("MASK",),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("PROMPT_SCHEDULE",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, prompt_schedule, mask1=None, mask2=None, mask3=None, mask4=None):
+        p = prompt_schedule.clone()
+        p.add_masks(mask1, mask2, mask3, mask4)
+        return (p,)
+
+
+class PCScheduleSettings:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {},
+            "optional": {
+                "steps": ("INT", {"default": 0, "min": 0, "max": 10000}),
+                "mask_width": ("INT", {"default": 512, "min": 64, "max": 4096 * 4}),
+                "mask_height": ("INT", {"default": 512, "min": 64, "max": 4096 * 4}),
+                "sdxl_width": ("INT", {"default": 1024, "min": 0, "max": 4096 * 4}),
+                "sdxl_height": ("INT", {"default": 1024, "min": 0, "max": 4096 * 4}),
+                "sdxl_target_w": ("INT", {"default": 1024, "min": 0, "max": 4096 * 4}),
+                "sdxl_target_h": ("INT", {"default": 1024, "min": 0, "max": 4096 * 4}),
+                "sdxl_crop_w": ("INT", {"default": 0, "min": 0, "max": 4096 * 4}),
+                "sdxl_crop_h": ("INT", {"default": 0, "min": 0, "max": 4096 * 4}),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("SCHEDULE_SETTINGS",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(
+        self,
+        steps=0,
+        mask_width=512,
+        mask_height=512,
+        sdxl_width=1024,
+        sdxl_height=1024,
+        sdxl_target_w=1024,
+        sdxl_target_h=1024,
+        sdxl_crop_w=0,
+        sdxl_crop_h=0,
+    ):
+        settings = {
+            "steps": steps,
+            "mask_width": mask_width,
+            "mask_height": mask_height,
+            "sdxl_width": sdxl_width,
+            "sdxl_height": sdxl_height,
+            "sdxl_twidth": sdxl_target_w,
+            "sdxl_theight": sdxl_target_h,
+            "sdxl_cwidth": sdxl_crop_w,
+            "sdxl_cheight": sdxl_crop_h,
+        }
+        return (settings,)
+
+
+class PCPromptFromSchedule:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "prompt_schedule": ("PROMPT_SCHEDULE",),
+                "at": ("FLOAT", {"min": 0.0, "max": 1.0, "step": 0.01}),
+            },
+            "optional": {"tags": ("STRING", {"default": ""})},
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("STRING",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "apply"
+
+    def apply(self, prompt_schedule, at, tags=""):
+        p = prompt_schedule.with_filters(tags, start=at, end=at).parsed_prompt[-1][1]
+        log.info("Prompt at %s:\n%s", at, p["prompt"])
+        log.info("LoRAs: %s", p["loras"])
+        return (p["prompt"],)
+
+
+class PromptToSchedule:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "text": ("STRING", {"multiline": True}),
+            },
+        }
+
+    DEPRECATED = True
+    RETURN_TYPES = ("PROMPT_SCHEDULE",)
+    CATEGORY = "promptcontrol/_legacy"
+    FUNCTION = "parse"
+
+    def parse(self, text, settings=None):
+        schedules = parse_prompt_schedules(text)
+        return (schedules,)

prompt_control/legacy/perp_weight.py

@@ -0,0 +1,70 @@
+import torch
+
+
+# Copied and adapted from https://github.com/bvhari/ComfyUI_PerpWeight/blob/main/clipperpweight.py
+def perp_encode(clip, tokens):
+    empty_tokens = clip.tokenize("")
+    sdxl_flag = "g" in tokens
+    empty_cond, empty_cond_pooled = clip.encode_from_tokens(empty_tokens, return_pooled=True)
+    unweighted_tokens = {}
+    for k in ["l", "g"]:
+        if k not in tokens:
+            continue
+        unweighted_tokens[k] = [[(t, 1.0) for t, _ in x] for x in tokens[k]]
+    unweighted_cond, unweighted_pooled = clip.encode_from_tokens(unweighted_tokens, return_pooled=True)
+    cond = torch.clone(unweighted_cond)
+
+    if sdxl_flag:
+        for i in range(unweighted_cond.shape[0]):
+            for j in range(unweighted_cond.shape[1]):
+                weight_l = tokens["l"][(j // 77)][(j % 77)][1]
+                if weight_l != 1.0:
+                    token_vector_l = unweighted_cond[i][j][:768]
+                    zero_vector_l = empty_cond[0][(j % 77)][:768]
+                    perp_l = (
+                        (torch.mul(zero_vector_l, token_vector_l).sum()) / (torch.norm(token_vector_l) ** 2)
+                    ) * token_vector_l
+                    if weight_l > 1.0:
+                        cond[i][j][:768] = token_vector_l + (weight_l * perp_l)
+                    elif (weight_l > 0.0) and (weight_l < 1.0):
+                        cond[i][j][:768] = token_vector_l - ((1 - weight_l) * perp_l)
+                    elif weight_l < 0.0:
+                        cond[i][j][:768] = token_vector_l + (weight_l * perp_l)
+                    elif weight_l == 0.0:
+                        cond[i][j][:768] = empty_cond[0][(j % 77)][:768]
+
+                weight_g = tokens["g"][(j // 77)][(j % 77)][1]
+                if weight_g != 1.0:
+                    token_vector_g = unweighted_cond[i][j][768:]
+                    zero_vector_g = empty_cond[0][(j % 77)][768:]
+                    perp_g = (
+                        (torch.mul(zero_vector_g, token_vector_g).sum()) / (torch.norm(token_vector_g) ** 2)
+                    ) * token_vector_g
+                    if weight_g > 1.0:
+                        cond[i][j][768:] = token_vector_g + (weight_g * perp_g)
+                    elif (weight_g > 0.0) and (weight_g < 1.0):
+                        cond[i][j][768:] = token_vector_g - ((1 - weight_g) * perp_g)
+                    elif weight_g < 0.0:
+                        cond[i][j][768:] = token_vector_g + (weight_g * perp_g)
+                    elif weight_g == 0.0:
+                        cond[i][j][768:] = empty_cond[0][(j % 77)][768:]
+    else:
+        tokens = tokens["l"]
+        for i in range(unweighted_cond.shape[0]):
+            for j in range(unweighted_cond.shape[1]):
+                weight = tokens[(j // 77)][(j % 77)][1]
+                if weight != 1.0:
+                    token_vector = unweighted_cond[i][j]
+                    zero_vector = empty_cond[0][(j % 77)]
+                    perp = (
+                        (torch.mul(zero_vector, token_vector).sum()) / (torch.norm(token_vector) ** 2)
+                    ) * token_vector
+                    if weight > 1.0:
+                        cond[i][j] = token_vector + (weight * perp)
+                    elif (weight > 0.0) and (weight < 1.0):
+                        cond[i][j] = token_vector - ((1 - weight) * perp)
+                    elif weight < 0.0:
+                        cond[i][j] = token_vector + (weight * perp)
+                    elif weight == 0.0:
+                        cond[i][j] = empty_cond[0][(j % 77)]
+    return cond, unweighted_pooled

prompt_control/legacy/utils.py

@@ -0,0 +1,265 @@
+from collections import namedtuple
+from os import environ
+from math import lcm
+import time
+import logging
+import torch
+
+from ..utils import lora_name_to_file, safe_float
+
+import nodes
+
+import comfy.model_management
+
+log = logging.getLogger("comfyui-prompt-control-legacy")
+
+FORCE_CPU_OFFLOAD = bool(environ.get("COMFYUI_PC_CPU_OFFLOAD"))
+
+
+# Minimal Modelpatcher that doesn't do anything, for LoRA loading when not
+# interested in either CLIP or unet
+class DummyModelPatcher:
+    class DummyTorchModel:
+        def __init__(self):
+            dummyconf = {
+                "num_res_blocks": [],
+                "channel_mult": [],
+                "transformer_depth": [],
+                "transformer_depth_output": [],
+                "transformer_depth_middle": 0,
+            }
+            self.model_config = namedtuple("DummyConfig", ["unet_config"])(dummyconf)
+
+        def state_dict(self):
+            return {}
+
+    def __init__(self):
+        self.model = self.DummyTorchModel()
+        self.cond_stage_model = self.DummyTorchModel()
+        self.weight_inplace_update = True
+        self.model_options = {}
+
+    def add_patches(self, patches, *args, **kwargs):
+        return []
+
+    def patch_model(self):
+        pass
+
+    def unpatch_model(self):
+        pass
+
+    def clone(self):
+        return self
+
+
+DUMMY_MODEL = DummyModelPatcher()
+
+
+def equalize(*tensors):
+    if all(t.shape[1] == tensors[0].shape[1] for t in tensors):
+        return tensors
+
+    x = lcm(*(t.shape[1] for t in tensors))
+
+    return (t.repeat(1, x // t.shape[1], 1) for t in tensors)
+
+
+def unpatch_model(model):
+    if model:
+        log.info("Unpatching model")
+        model.unpatch_model()
+
+
+def clone_model(model):
+    if not model:
+        return None
+    model = model.clone()
+    if not environ.get("PC_NO_INPLACE_UPDATE"):
+        model.weight_inplace_update = True
+    return model
+
+
+def add_patches(model, patches, weight):
+    model.add_patches(patches, weight)
+
+
+def patch_model(model, forget=False, orig=None):
+    global FORCE_CPU_OFFLOAD
+    try:
+        return _patch_model(model, forget, orig, FORCE_CPU_OFFLOAD)
+    except comfy.model_management.OOM_EXCEPTION:
+        FORCE_CPU_OFFLOAD = True
+        log.error("Ran out of memory while applying LoRAs, Forcing CPU offload from now on")
+        # Unpatch to restore partially applied weights
+        unpatch_model(model)
+        raise
+
+
+def _patch_model(model, forget=False, orig=None, offload_to_cpu=False):
+    if not model:
+        return None
+    if offload_to_cpu:
+        saved_offload = model.offload_device
+        model.offload_device = torch.device("cpu")
+    log.info(
+        "Patching model, model.load_device=%s model.model.device=%s cpu_offload=%s",
+        model.load_device,
+        model.model.device,
+        model.offload_device == torch.device("cpu"),
+    )
+    if orig:
+        model.backup = orig.backup
+    model.patch_model(device_to=model.load_device)
+    if offload_to_cpu:
+        model.offload_device = saved_offload
+    if forget:
+        model.patches = {}
+        model.object_patches = {}
+    return model
+
+
+def get_callback(model):
+    return model.model_options.get("prompt_control_callback")
+
+
+def set_callback(model, cb):
+    model.model_options["prompt_control_callback"] = cb
+
+
+# Hack to temporarily override printing to stdout to stop log spam
+def suppress_print(f):
+    def noop(*args):
+        pass
+
+    p = print
+    __builtins__["print"] = noop
+    rootlogger = logging.getLogger()
+    oldlevel = rootlogger.level
+    try:
+        rootlogger.setLevel(logging.ERROR)
+        x = f()
+    except BaseException:
+        __builtins__["print"] = p
+        rootlogger.setLevel(oldlevel)
+        raise
+    __builtins__["print"] = p
+    rootlogger.setLevel(oldlevel)
+    return x
+
+
+def load_lbw():
+    return nodes.NODE_CLASS_MAPPINGS.get("LoraLoaderBlockWeight //Inspire")
+
+
+def make_loader(filename, lbw):
+    if not lbw:
+        l = nodes.LoraLoader()
+
+        def loader(model, clip, model_weight, clip_weight, lbw):
+            return suppress_print(lambda: l.load_lora(model, clip, filename, model_weight, clip_weight))
+
+    else:
+        # This is already checked before calling make_loader
+        l = load_lbw()()
+
+        def loader(model, clip, model_weight, clip_weight, lbw):
+            spec = lbw["LBW"]
+            lbw_a = safe_float(lbw.get("A"), 4.0)
+            lbw_b = safe_float(lbw.get("B"), 1.0)
+            m = model or DUMMY_MODEL
+            c = clip or DUMMY_MODEL
+            m, c, _ = suppress_print(
+                lambda: l.doit(m, c, filename, model_weight, clip_weight, False, 0, lbw_a, lbw_b, "", spec)
+            )
+            if m is DUMMY_MODEL:
+                m = None
+            if c is DUMMY_MODEL:
+                c = None
+            return m, c
+
+    return loader
+
+
+def apply_loras_from_spec(
+    loraspec, model=None, clip=None, orig_model=None, orig_clip=None, patch=False, cache=None, applied_loras=None
+):
+    if applied_loras is None:
+        applied_loras = {}
+    actual_loraspec = {}
+    additive = True
+    for key in loraspec:
+        if key in applied_loras and applied_loras[key] == loraspec[key]:
+            continue
+        if key in applied_loras and applied_loras[key] != loraspec[key]:
+            additive = False
+        actual_loraspec[key] = loraspec[key]
+
+    for key in applied_loras:
+        if key not in loraspec:
+            actual_loraspec = loraspec
+            additive = False
+
+    backup_model = model
+    if not additive:
+        unpatch_model(model)
+        # Reset clip to unpatched
+        if clip:
+            clip = orig_clip or clip
+
+    if cache is None:
+        cache = {}
+    if not loraspec:
+        return model, clip
+
+    for name, params in actual_loraspec.items():
+        m, c = model, clip
+        w, w_clip = params["weight"], params["weight_clip"]
+        if w == 0:
+            m = None
+        if w_clip == 0:
+            c = None
+        if not w and not c:
+            continue
+
+        lbw = params.get("lbw")
+        if lbw and not load_lbw():
+            log.warning("LoraBlockWeight not available, ignoring LBW parameters")
+            lbw = None
+
+        # Cache the loader instance so that it doesn't reload the LoRA from disk all the time
+        cache_key = name, bool(lbw)
+        loader = cache.get(cache_key)
+        if not loader:
+            f = lora_name_to_file(name)
+            if not f:
+                log.warning("Lora %s not found", name)
+                continue
+            log.info("Loading LoRA: %s", f)
+            loader = make_loader(f, bool(lbw))
+            cache[cache_key] = loader
+
+        m, c = loader(m, c, w, w_clip, lbw)
+        model = m or model
+        clip = c or clip
+        if model:
+            log.info("Applying LoRA: %s:%s, LBW=%s, additive=%s", name, params["weight"], bool(lbw), additive)
+        if clip:
+            log.info("Applying CLIP LoRA: %s:%s, LBW=%s, additive=%s", name, params["weight_clip"], bool(lbw), additive)
+
+    # forget patches so we don't double-patch
+    model = patch_model(model, forget=True, orig=backup_model)
+    return model, clip
+
+
+class Timer:
+    def __init__(self, name):
+        self.name = name
+        self.start = None
+
+    def __enter__(self):
+        self.start = time.time()
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        elapsed = time.time() - self.start
+        if environ.get("PC_SHOW_TIMINGS"):
+            log.info("Executed %s in %s seconds", self.name, elapsed)

prompt_control/macros.py

@@ -1,131 +0,0 @@
-# vim: sw=4 ts=4
-from __future__ import annotations
-
-import logging
-import re
-
-from .utils import find_closing_paren, get_function, split_by_function
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def substitute_template(template, segments, do_subs):
-    def _substitute(template, segments, stack):
-        name = ""
-        if "$" in template:
-            for name, value in sorted(segments):
-                value = substitute_var(value, name, "")
-                if name not in stack:
-                    stack.add(name)
-                    value = _substitute(value, segments, stack)
-                    stack.remove(name)
-                template = substitute_var(template, name, value)
-        if do_subs and name not in stack:
-            template = expand_subs(template)
-        return template
-
-    return _substitute(template, segments, set())
-
-
-def expand_segs(text, do_subs=True):
-    template, segments = split_by_function(text, "SEG", defaults=[""], require_args=True)
-    named_segs = [(f.args[0].strip() or f"SEG{i + 1}", c.strip()) for i, (c, f) in enumerate(segments)]
-
-    new_text = substitute_template(template, named_segs, do_subs).strip()
-    if new_text != text.strip():
-        log.debug("Template expanded to: %s", new_text)
-    return new_text
-
-
-def expand_subs(text):
-    text, subs = get_function(text, "SUB", defaults=None)
-    subs = [spec.strip() for f in subs for spec in f.args[0].split(";")]
-    for spec in subs:
-        if len(spec) <= 3 or spec[0] != "s":
-            log.warning("Invalid SUB spec ignored: '%s'", spec)
-            continue
-        splitchar = spec[1]
-        search, replace, *_ = spec[2:].split(splitchar)
-        text = re.sub(search, replace, text)
-    return text
-
-
-def parse_search(search):
-    arg_start = search.find("(")
-    args = ""
-    name = search.strip()
-    if arg_start > 0:
-        arg_end = find_closing_paren(search, arg_start + 1)
-        if arg_end < 0:
-            arg_end = len(search)
-        name = search[:arg_start].strip()
-        args = search[arg_start + 1 : arg_end]
-
-    if not name:
-        return None
-    args = args.strip()
-    # If using the form DEF(F()=$1) then the default value of $1 is the empty string
-    args = [a.strip() for a in args.split(";")] if arg_start > 0 else []
-    return name, args
-
-
-def expand_macros(text, defs=None):
-    silent = False
-    if defs is None:
-        text, defs = get_function(text, "DEF", defaults=None)
-    else:
-        silent = True
-    res = text
-    prevres = text
-    replacements = []
-    for d in defs:
-        if not d.args:
-            continue
-        r = d.args[0].split("=", 1)
-        search = parse_search(r[0].strip())
-        if not search or len(r) != 2:
-            log.warning("Ignoring invalid DEF(%s)", d)
-            continue
-        replacements.append((search, r[1].strip()))
-    iterations = 0
-    while True:
-        iterations += 1
-        if iterations > 10:
-            raise ValueError("Unable to resolve DEFs, make sure there are no cycles!")
-        for search, replace in replacements:
-            res = substitute_defcall(res, search, replace)
-        if res == prevres:
-            break
-        prevres = res
-    if res.strip() != text.strip():
-        res = res.strip()
-        if not silent:
-            log.debug("DEFs expanded to: %s", res)
-    return res
-
-
-def substitute_var(text, name, replace, boundary=r"\b"):
-    if f"${name}" not in text:
-        return text
-    name = re.escape(str(name))
-    return re.sub(rf"\${name}{boundary}", replace, text)
-
-
-def substitute_defcall(text, search, replace):
-    name, default_args = search
-
-    def run_macro(*parameters):
-        paramvals = []
-        if parameters:
-            paramvals = [x.strip() for x in parameters[0].split(";")]
-        r = replace
-        end_re = r"(?![0-9])"
-        for i, v in enumerate(paramvals):
-            r = substitute_var(r, i + 1, v, boundary=end_re)
-
-        for i, v in enumerate(default_args):
-            r = substitute_var(r, i + 1, v, boundary=end_re)
-        return r
-
-    text, _ = get_function(text, name, defaults=None, processor=run_macro, require_args=False)
-    return text

prompt_control/nodes_anima.py

@@ -1,52 +0,0 @@
-# Adapted from ComfyUI-ppm into hook form
-
-
-import comfy.model_management
-import comfy.patcher_extension
-from comfy.model_base import Anima
-from comfy.model_patcher import ModelPatcher
-from comfy_api.latest import io
-
-from .anima_couple import (
-    anima_forward_wrapper,
-    anima_sample_wrapper,
-)
-
-
-class PCAnimaAttnCouplePatch(io.ComfyNode):
-    @classmethod
-    def define_schema(cls) -> io.Schema:
-        return io.Schema(
-            node_id="PCAnimaAttnCouplePatch",
-            display_name="PC: Anima attention Couple Model Patch",
-            category="promptcontrol/experimental",
-            inputs=[
-                io.Model.Input("model"),
-            ],
-            outputs=[
-                io.Model.Output(),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, model: ModelPatcher) -> io.NodeOutput:
-        model_type = type(model.model)
-        m = model
-
-        if issubclass(model_type, Anima):
-            m = model.clone()
-            m.add_wrapper_with_key(
-                comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL,
-                cls.__name__,
-                anima_forward_wrapper,
-            )
-            m.add_wrapper_with_key(
-                comfy.patcher_extension.WrappersMP.SAMPLER_SAMPLE,
-                cls.__name__,
-                anima_sample_wrapper,
-            )
-
-        return io.NodeOutput(m)
-
-
-NODES = [PCAnimaAttnCouplePatch]

prompt_control/nodes_base.py

@@ -1,86 +0,0 @@
-import logging
-
-from comfy_api.latest import io
-
-from .macros import expand_segs
-from .prompts import encode_prompt, hook_te
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-class PCTextEncodeWithRange(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCTextEncodeWithRange",
-            display_name="PC: Text Encode with Range (no scheduling)",
-            category="promptcontrol/tools",
-            description="Like PCTextEncode, but if you know the range you need for a prompt, can be slightly more efficient when you have LoRAs scheduled on a CLIP model.",
-            inputs=[
-                io.Clip.Input("clip"),
-                io.String.Input("text", multiline=True),
-                io.Float.Input("start", default=0.0, min=0.0, max=1.0, step=0.01, optional=True),
-                io.Float.Input("end", default=1.0, min=0.0, max=1.0, step=0.01, optional=True),
-            ],
-            outputs=[io.Conditioning.Output()],
-        )
-
-    @classmethod
-    def execute(cls, clip, text, start=0.0, end=1.0) -> io.NodeOutput:
-        log.debug("PCTextEncode: Encoding '%s'", text)
-        defaults = clip.patcher.model_options.get("x-promptcontrol.defaults", {})
-        masks = clip.patcher.model_options.get("x-promptcontrol.masks", None)
-        text = expand_segs(text)
-        out = encode_prompt(clip, text, start, end, defaults, masks)
-        return io.NodeOutput(out)
-
-
-class PCTextEncode(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCTextEncode",
-            display_name="PC: Text Encode (no scheduling)",
-            category="promptcontrol",
-            description="Encodes a prompt with extra goodies from Prompt Control. This node does *not* support scheduling.",
-            inputs=[
-                io.Clip.Input("clip"),
-                io.String.Input("text", multiline=True),
-            ],
-            outputs=[io.Conditioning.Output()],
-        )
-
-    @classmethod
-    def execute(cls, clip, text) -> io.NodeOutput:
-        # Use the WithRange node for the range 0.0, 1.0
-        return PCTextEncodeWithRange.execute(clip, text, 0.0, 1.0)
-
-
-class PCHookEncoderModsInternal(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCHookTextEncoderModsInternal",
-            display_name="PC: Apply Text Encoder Mods",
-            category="promptcontrol",
-            description="Apply TE modifications (internal)",
-            is_experimental=True,
-            is_dev_only=True,
-            inputs=[
-                io.Clip.Input("clip"),
-                io.String.Input("te_names"),
-                io.String.Input("style"),
-                io.String.Input("normalization"),
-                io.Custom("PC_EXTRA_DATA").Input("extra", optional=True),
-            ],
-            outputs=[io.Clip.Output()],
-        )
-
-    @classmethod
-    def execute(cls, clip, te_names, style, normalization, extra) -> io.NodeOutput:
-        te_names = [x.strip() for x in te_names.split(",")]
-        clip = hook_te(clip, te_names, style, normalization, extra)
-        return io.NodeOutput(clip)
-
-
-NODES = [PCTextEncodeWithRange, PCTextEncode, PCHookEncoderModsInternal]

prompt_control/nodes_hooks.py

@@ -1,131 +0,0 @@
-import logging
-
-import comfy.hooks
-import comfy.utils
-import folder_paths
-from comfy_api.latest import io
-from typing_extensions import override
-
-from .attention_couple_ppm import AttentionCoupleHook
-from .parser import parse_prompt_schedules
-from .utils import consolidate_schedule
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-class PCLoraHooksFromText(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCLoraHooksFromText",
-            display_name="PC: LoRA Hooks From Text (non-lazy)",
-            category="promptcontrol/v2",
-            description="set of hooks created from the prompt schedule",
-            is_experimental=True,
-            inputs=[
-                io.String.Input("text", multiline=True),
-            ],
-            outputs=[io.Hooks.Output()],
-        )
-
-    @classmethod
-    def execute(cls, text) -> io.NodeOutput:
-        prompt_schedule = parse_prompt_schedules(text)
-        consolidated = consolidate_schedule(prompt_schedule)
-        hooks = lora_hooks_from_schedule(consolidated, {})
-        return io.NodeOutput(hooks)
-
-
-def lora_hooks_from_schedule(schedules, non_scheduled):
-    start_pct = 0.0
-    lora_cache = {}
-    all_hooks = []
-
-    def create_hook(loras, start_pct, end_pct, non_scheduled):
-        hooks = []
-        hook_kf = comfy.hooks.HookKeyframeGroup()
-        for path, info in loras.items():
-            if non_scheduled.get(path) == info:
-                log.info("Skipping %s from hook, it's loaded directly on model", path)
-                continue
-            if path not in lora_cache:
-                lora_cache[path] = comfy.utils.load_torch_file(
-                    folder_paths.get_full_path("loras", path), safe_load=True
-                )
-            new_hook = comfy.hooks.create_hook_lora(
-                lora_cache[path], strength_model=info["weight"], strength_clip=info["weight_clip"]
-            )
-            ref = f"pc-{path}-{info['weight']}-{info['weight_clip']}"
-            new_hook.hooks[0].hook_ref = ref
-            hooks.append(new_hook)
-        if start_pct > 0.0:
-            kf = comfy.hooks.HookKeyframe(strength=0.0, start_percent=0.0)
-            hook_kf.add(kf)
-        kf = comfy.hooks.HookKeyframe(strength=1.0, start_percent=start_pct)
-        hook_kf.add(kf)
-        if end_pct < 1.0:
-            kf = comfy.hooks.HookKeyframe(strength=0.0, start_percent=end_pct)
-            hook_kf.add(kf)
-        hooks = comfy.hooks.HookGroup.combine_all_hooks(hooks)
-        if hooks:
-            hooks.set_keyframes_on_hooks(hook_kf=hook_kf)
-        return hooks
-
-    for end_pct, loras in schedules:
-        log.info("Creating LoRA hook from %s to %s: %s", start_pct, end_pct, loras)
-        hook = create_hook(loras, start_pct, end_pct, non_scheduled)
-        all_hooks.append(hook)
-        start_pct = end_pct
-
-    all_hooks = [x for x in all_hooks if x]
-    if all_hooks:
-        hooks = comfy.hooks.HookGroup.combine_all_hooks(all_hooks)
-        return hooks
-
-
-class PCAttentionCoupleBatchNegative(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCAttentionCoupleBatchNegative",
-            display_name="PC: Attention Couple (batch negative)",
-            category="promptcontrol/v2",
-            description="Batch negatives, carrying over Attention Couple hooks",
-            is_experimental=True,
-            inputs=[
-                io.Conditioning.Input("positive"),
-                io.Conditioning.Input("negative"),
-            ],
-            outputs=[
-                io.Conditioning.Output("positive"),
-                io.Conditioning.Output("negative"),
-            ],
-        )
-
-    @classmethod
-    @override
-    def execute(cls, positive, negative) -> io.NodeOutput:
-        if len(negative) != 1:
-            log.warning("Batching scheduled negatives is not supported yet")
-            return io.NodeOutput(positive, negative)
-
-        negative_batch = []
-        for p in positive:
-            n = [negative[0][0], negative[0][1].copy()]
-            n_hook_group = n[1].get("hooks", comfy.hooks.HookGroup()).clone()
-            p_hook_group = p[1].get("hooks", comfy.hooks.HookGroup())
-            attn_couple = [hook for hook in p_hook_group.hooks if isinstance(hook, AttentionCoupleHook)]
-            for hook in attn_couple:
-                n_hook_group.add(hook)
-            n[1]["hooks"] = p_hook_group if n_hook_group.hooks == p_hook_group.hooks else n_hook_group
-            n[1]["start_percent"] = p[1].get("start_percent", 0.0)
-            n[1]["end_percent"] = p[1].get("end_percent", 1.0)
-            negative_batch.append(n)
-
-        return io.NodeOutput(positive, negative_batch)
-
-
-NODES = [
-    PCLoraHooksFromText,
-    PCAttentionCoupleBatchNegative,
-]

prompt_control/nodes_lazy.py

@@ -1,403 +0,0 @@
-# pyright: reportSelfClsParameterName=false
-from __future__ import annotations
-
-import json
-import logging
-
-from comfy_api.latest import io
-from comfy_execution.graph import ExecutionBlocker
-from comfy_execution.graph_utils import GraphBuilder
-
-from .macros import expand_macros, expand_segs
-from .parser import parse_prompt_schedules
-from .utils import consolidate_schedule, find_nonscheduled_loras, get_function, split_by_function
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def create_lora_loader_nodes(graph, model, clip, loras):
-    for path, info in loras.items():
-        log.info("Creating LoraLoader for %s", path)
-        loader = graph.node("LoraLoader")
-        loader.set_input("model", model)
-        loader.set_input("clip", clip)
-        loader.set_input("strength_model", info["weight"])
-        loader.set_input("strength_clip", info["weight_clip"])
-        loader.set_input("lora_name", path)
-        model = loader.out(0)
-        clip = loader.out(1)
-    return model, clip
-
-
-def create_hook_nodes_for_lora(graph, path, info, existing_node, start_pct, end_pct):
-    prev_keyframe = None
-    next_keyframe = None
-    if not existing_node:
-        log.debug("Creating hook for %s, weight=%s, weight_clip=%s", path, info["weight"], info["weight_clip"])
-        hook_node = graph.node("CreateHookLora")
-        hook_node.set_input("lora_name", path)
-        hook_node.set_input("strength_model", info["weight"])
-        hook_node.set_input("strength_clip", info["weight_clip"])
-        prev_hook_kf = None
-        if start_pct > 0:
-            log.debug("Creating KF (0, %s) for %s", start_pct, path)
-            prev_keyframe = graph.node("CreateHookKeyframe")
-            prev_keyframe.set_input("strength_mult", 0.0)
-            prev_keyframe.set_input("start_percent", 0.0)
-            prev_hook_kf = prev_keyframe.out(0)
-    else:
-        log.debug("Hook already created for %s", path)
-        hook_node, prev_keyframe = existing_node
-        prev_hook_kf = prev_keyframe.out(0)
-
-    if (
-        prev_keyframe
-        and prev_keyframe.get_input("start_pct") == start_pct
-        and prev_keyframe.get_input("strength_mult") == 0.0
-    ):
-        next_keyframe = prev_keyframe
-        log.debug("Previous keyframe for %s starts at %s and has 0 strength, overriding", path, start_pct)
-    else:
-        log.debug("Creating keyframe for %s, start=%s ", path, start_pct)
-        next_keyframe = graph.node("CreateHookKeyframe")
-        next_keyframe.set_input("start_percent", start_pct)
-        next_keyframe.set_input("prev_hook_kf", prev_hook_kf)
-
-    next_keyframe.set_input("strength_mult", 1.0)
-    prev_hook_kf = next_keyframe.out(0)
-    if end_pct < 1.0:
-        log.debug("Creating end keyframe for %s, start=%s", path, end_pct)
-        next_keyframe = graph.node("CreateHookKeyframe")
-        next_keyframe.set_input("strength_mult", 0.0)
-        next_keyframe.set_input("start_percent", end_pct)
-        next_keyframe.set_input("prev_hook_kf", prev_hook_kf)
-    return hook_node, next_keyframe
-
-
-def build_lora_schedule(graph, schedule, model, clip, apply_hooks=True):
-    # This gets rid of non-existent LoRAs
-    consolidated = consolidate_schedule(schedule)
-    if model is not None:
-        non_scheduled = find_nonscheduled_loras(consolidated)
-        model, clip = create_lora_loader_nodes(graph, model, clip, non_scheduled)
-    else:
-        non_scheduled = {}
-        model = ExecutionBlocker("No model provided to PCLazyLoRALoader or PCLazyLoRALoaderAdvanced")
-
-    hook_nodes = {}
-    start_pct = 0.0
-
-    def key(lora, info):
-        return f"{lora}-{info['weight']}-{info['weight_clip']}"
-
-    for end_pct, loras in consolidated:
-        for lora, info in loras.items():
-            if non_scheduled.get(lora) == info:
-                continue
-            k = key(lora, info)
-            existing_node = hook_nodes.get(k)
-            hook_nodes[k] = create_hook_nodes_for_lora(graph, lora, info, existing_node, start_pct, end_pct)
-        start_pct = end_pct
-
-    hooks = []
-    # Attach the keyframe chain to the hook node
-    for hook, kfs in hook_nodes.values():
-        n = graph.node("SetHookKeyframes")
-        n.set_input("hooks", hook.out(0))
-        n.set_input("hook_kf", kfs.out(0))
-        hooks.append(n)
-
-    res = None
-    # Finally, combine all hooks and optionally apply
-    if len(hooks) > 0:
-        res = hooks[0]
-        for h in hooks[1:]:
-            n = graph.node("CombineHooks2")
-            n.set_input("hooks_A", res.out(0))
-            n.set_input("hooks_B", h.out(0))
-            res = n
-        res = res.out(0)
-        if clip is not None and apply_hooks:
-            n = graph.node("SetClipHooks")
-            n.set_input("clip", clip)
-            n.set_input("hooks", res)
-            n.set_input("apply_to_conds", True)
-            n.set_input("schedule_clip", True)
-            clip = n.out(0)
-
-    if clip is None:
-        clip = ExecutionBlocker("No clip model provided to PCLazyLoRALoader or PCLazyLoRALoaderAdvanced")
-    r = graph.finalize()
-    log.debug("LazyLoraLoader built graph: %s", json.dumps(r))
-
-    ret = (model, clip, res)
-
-    return io.NodeOutput(*ret, expand=r)
-
-
-class PCLazyLoraLoaderAdvanced(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCLazyLoraLoaderAdvanced",
-            display_name="PC: Schedule LoRAs (Advanced)",
-            enable_expand=True,
-            category="promptcontrol",
-            description="Returns a model and clip with LoRAs scheduled",
-            inputs=[
-                io.Model.Input("model", extra_dict={"rawLink": True}, optional=True),
-                io.Clip.Input("clip", extra_dict={"rawLink": True}, optional=True),
-                io.String.Input("text", multiline=True, default=""),
-                io.Boolean.Input("apply_hooks", default=True),
-                io.String.Input("tags", default=""),
-                io.Float.Input("start", min=0.0, max=1.0, default=0.0, step=0.01),
-                io.Float.Input("end", min=0.0, max=1.0, default=1.0, step=0.01),
-                io.Int.Input("num_steps", min=0, max=10000, default=0, step=1),
-            ],
-            outputs=[io.Model.Output("model"), io.Clip.Output("clip"), io.Hooks.Output("hooks")],
-        )
-
-    @classmethod
-    def execute(cls, model=None, clip=None, text="", apply_hooks=True, tags="", start=0.0, end=1.0, num_steps=0):
-        text = expand_segs(expand_macros(text))
-        schedule = parse_prompt_schedules(text, filters=tags, start=start, end=end, num_steps=num_steps)
-        graph = GraphBuilder()
-        r = build_lora_schedule(graph, schedule, model, clip, apply_hooks=apply_hooks)
-        return r
-
-
-class PCLazyLoraLoader(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCLazyLoraLoader",
-            display_name="PC: Schedule LoRAs",
-            enable_expand=True,
-            category="promptcontrol",
-            description="Returns a model and clip with LoRAs scheduled",
-            inputs=[
-                io.Model.Input("model", extra_dict={"rawLink": True}, optional=True),
-                io.Clip.Input("clip", extra_dict={"rawLink": True}, optional=True),
-                io.String.Input("text", multiline=True, default=""),
-            ],
-            outputs=[
-                io.Model.Output("model"),
-                io.Clip.Output("clip"),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, model, clip, text):
-        no = PCLazyLoraLoaderAdvanced.execute(model, clip, text)
-        return io.NodeOutput(*no.args[:2], expand=no.expand)
-
-
-def parse_extra_inputs(args, defaults):
-    params = {}
-    if not args.strip():
-        return defaults + [{}]
-    defaults = defaults[:]
-    defaults.append("")
-    for i, v in enumerate(args.split(",", maxsplit=len(defaults) - 1)):
-        defaults[i] = v
-        # We should strip extra whitespace so that people don't have to worry about functions.
-    magic_spec = defaults[-1]
-    magic_spec.replace(r"\;", "__ESCAPED_SEMICOLON__")
-    extra_inputs = magic_spec.split(";") if magic_spec.strip() else []
-    for e in extra_inputs:
-        e = e.strip()
-        if not e:
-            continue
-        e = e.replace("__ESCAPED_SEMICOLON__", ";")
-        name, jsondata = e.split(maxsplit=1)
-        jsondata = jsondata.strip()
-        if not jsondata.strip():
-            continue
-        # From helper node:
-        if jsondata == "__EMPTY__":
-            continue
-        try:
-            params[name.strip()] = json.loads(jsondata.strip())
-        except ValueError as e:
-            raise ValueError(f"Invalid JSON input: '{jsondata}'") from e
-    return [x.strip() for x in defaults[:-1]] + [params]
-
-
-def make_node(graph, p, clip, strip):
-    p, classnames = get_function(p, "NODE", defaults=None)
-    p, filters = get_function(p, "FILTER", defaults=None)
-    args = ""
-    if len(classnames) > 1:
-        log.warning("You have more than one NODE call in your prompt. Only the first one will be used")
-    if classnames:
-        args = classnames[0].args[0]
-        if not args.strip():
-            raise ValueError("NODE can't be empty!")
-    classname, paramname, extras = parse_extra_inputs(args, ["PCTextEncode", "text"])
-    # We should strip extra whitespace so that people don't have to worry about functions.
-    node = graph.node(classname.strip())
-    node.set_input("clip", clip)
-    node.set_input(paramname.strip(), p.strip() if strip else p)
-    for e, v in extras.items():
-        node.set_input(e, v)
-
-    for f in filters:
-        classname, paramname, extras = parse_extra_inputs(f.args[0], ["", "conditioning"])
-        if not classname:
-            raise ValueError("FILTER requires a Node class name")
-        extras[paramname] = node.out(0)
-        node = graph.node(classname)
-        for e, v in extras.items():
-            node.set_input(e, v)
-
-    return node
-
-
-def build_prompt(graph, prompt, clip, start=None, end=None):
-    p = prompt
-    strip = "NOSTRIP()" not in p
-    p = p.replace("NOSTRIP()", "")
-    # Need to explicitly expand SEGs here *before* NODE is processed
-    p = expand_segs(p)
-    p, combines = split_by_function(p, "COMBINE")
-    current_cond = make_node(graph, p, clip, strip)
-    for text, f in combines:
-        classname, param1, param2, extra = parse_extra_inputs(f.args[0], ["", "conditioning_1", "conditioning_2"])
-        if classname.strip() == "":
-            raise ValueError("Can't use COMBINE without a class name")
-        combiner = graph.node(classname.strip())
-        c2 = make_node(graph, text, clip, strip)
-        extra[param1] = current_cond.out(0)
-        extra[param2] = c2.out(0)
-        for e, v in extra.items():
-            combiner.set_input(e, v)
-        current_cond = combiner
-
-    node = current_cond
-    if start is not None and end is not None:
-        node = graph.node("ConditioningSetTimestepRange")
-        node.set_input("conditioning", current_cond.out(0))
-        node.set_input("start", start)
-        node.set_input("end", end)
-
-    return node
-
-
-def build_scheduled_prompts(graph, schedules, clip):
-    nodes = []
-    start_pct = 0.0
-    for end_pct, c in schedules:
-        p = c["prompt"]
-        node = build_prompt(graph, p, clip, start_pct, end_pct)
-        nodes.append(node)
-        start_pct = end_pct
-
-    node = nodes[0]
-    for othernode in nodes[1:]:
-        combiner = graph.node("ConditioningCombine")
-        combiner.set_input("conditioning_1", node.out(0))
-        combiner.set_input("conditioning_2", othernode.out(0))
-        node = combiner
-
-    g = graph.finalize()
-    log.debug("Built graph: %s", json.dumps(g))
-
-    return io.NodeOutput(node.out(0), expand=g)
-
-
-class PCLazyTextEncodeAdvanced(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCLazyTextEncodeAdvanced",
-            display_name="PC: Schedule prompt (Advanced)",
-            enable_expand=True,
-            category="promptcontrol",
-            inputs=[
-                io.Clip.Input("clip", extra_dict={"rawLink": True}),
-                io.String.Input("text", multiline=True, default=""),
-                io.String.Input("tags", default=""),
-                io.Float.Input("start", min=0.0, max=1.0, default=0.0, step=0.01),
-                io.Float.Input("end", min=0.0, max=1.0, default=1.0, step=0.01),
-                io.Int.Input("num_steps", min=0, max=10000, default=0, step=1),
-            ],
-            outputs=[
-                io.Conditioning.Output("conditioning"),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, clip, text, tags="", start=0.0, end=1.0, num_steps=0):
-        schedules = parse_prompt_schedules(text, filters=tags, start=start, end=end, num_steps=num_steps)
-        graph = GraphBuilder()
-        return build_scheduled_prompts(graph, schedules, clip)
-
-
-class PCLazyTextEncode(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCLazyTextEncode",
-            display_name="PC: Schedule prompt",
-            enable_expand=True,
-            category="promptcontrol",
-            inputs=[
-                io.Clip.Input("clip", extra_dict={"rawLink": True}),
-                io.String.Input("text", multiline=True, default=""),
-            ],
-            outputs=[
-                io.Conditioning.Output("conditioning"),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, clip, text):
-        return PCLazyTextEncodeAdvanced.execute(clip, text)
-
-
-predefined_macros = get_function(
-    """
-DEF(AND=COMBINE(ConditioningCombine, conditioning_1, conditioning_2))
-DEF(CAT=COMBINE(ConditioningConcat, conditioning_to, conditioning_from))
-DEF(AVG(0.5)=COMBINE(ConditioningAverage, conditioning_from, conditioning_to, conditioning_to_strength $1))
-""",
-    "DEF",
-    defaults=None,
-)
-
-
-class PCLazyTextEncodeSingle(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCLazyTextEncodeSingle",
-            display_name="PC: Prompt (without scheduling)",
-            is_experimental=True,
-            is_dev_only=True,
-            enable_expand=True,
-            category="promptcontrol",
-            inputs=[
-                io.Clip.Input("clip", raw_link=True),
-                io.String.Input("text", multiline=True, default=""),
-            ],
-            outputs=[
-                io.Conditioning.Output("conditioning"),
-            ],
-        )
-
-    @classmethod
-    def execute(cls, clip, text):
-        graph = GraphBuilder()
-        text = expand_macros(text, predefined_macros)
-        node = build_prompt(graph, text, clip)
-        g = graph.finalize()
-        return io.NodeOutput(node.out(0), expand=g)
-
-
-NODES = [
-    PCLazyTextEncode,
-    PCLazyTextEncodeAdvanced,
-    PCLazyTextEncodeSingle,
-    PCLazyLoraLoader,
-    PCLazyLoraLoaderAdvanced,
-]

prompt_control/nodes_tools.py

@@ -1,259 +0,0 @@
-import json
-import logging
-
-from comfy_api.latest import io
-
-from .macros import expand_macros as macroexpand
-from .macros import expand_segs as segexpand
-from .macros import expand_subs as subexpand
-from .macros import substitute_var
-from .parser import parse_prompt_schedules
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-class PCSetLogLevel(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCSetLogLevel",
-            display_name="PC: Configure Logging (for debug)",
-            category="promptcontrol/tools",
-            description="A debug node to configure Prompt Control logging level. Pass a CLIP through it before you run any PC nodes",
-            inputs=[
-                io.Clip.Input("clip"),
-                io.Combo.Input("level", options=["INFO", "DEBUG", "WARNING", "ERROR"], default="INFO", optional=True),
-            ],
-            outputs=[io.Clip.Output()],
-        )
-
-    @classmethod
-    def execute(cls, clip, level="INFO") -> io.NodeOutput:
-        log.setLevel(getattr(logging, level))
-        log.info("Set logging level to %s", level)
-        return io.NodeOutput(clip)
-
-
-class PCAddMaskToCLIP(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCAddMaskToCLIP",
-            display_name="PC: Attach Mask",
-            category="promptcontrol/tools",
-            description="Attaches a mask to a CLIP object so that they can be referred to in a prompt using IMASK(). Using this node multiple times adds more masks rather than replacing existing ones.",
-            inputs=[
-                io.Clip.Input("clip"),
-                io.Mask.Input("mask", optional=True),
-            ],
-            outputs=[io.Clip.Output()],
-        )
-
-    @classmethod
-    def execute(cls, clip, mask=None) -> io.NodeOutput:
-        return PCAddMaskToCLIPMany.execute(clip, mask1=mask)
-
-
-class PCAddMaskToCLIPMany(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCAddMaskToCLIPMany",
-            display_name="PC: Attach Mask (multi)",
-            category="promptcontrol/tools",
-            description="Multi-input version of PCAddMaskToCLIP, for convenience",
-            inputs=[
-                io.Clip.Input("clip"),
-                io.Mask.Input("mask1", optional=True),
-                io.Mask.Input("mask2", optional=True),
-                io.Mask.Input("mask3", optional=True),
-                io.Mask.Input("mask4", optional=True),
-            ],
-            outputs=[io.Clip.Output()],
-        )
-
-    @classmethod
-    def execute(cls, clip, mask1=None, mask2=None, mask3=None, mask4=None) -> io.NodeOutput:
-        clip = clip.clone()
-        current_masks = clip.patcher.model_options.get("x-promptcontrol.masks", [])
-        current_masks.extend(m for m in (mask1, mask2, mask3, mask4) if m is not None)
-        clip.patcher.model_options["x-promptcontrol.masks"] = current_masks
-        return io.NodeOutput(clip)
-
-
-class PCSetPCTextEncodeSettings(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCSetPCTextEncodeSettings",
-            display_name="PC: Configure PCTextEncode",
-            category="promptcontrol/tools",
-            description="Configures default values for PCTextEncode",
-            inputs=[
-                io.Clip.Input("clip"),
-                io.Int.Input("mask_width", default=512, min=64, max=4096 * 4, optional=True),
-                io.Int.Input("mask_height", default=512, min=64, max=4096 * 4, optional=True),
-                io.Int.Input("sdxl_width", default=1024, min=0, max=4096 * 4, optional=True),
-                io.Int.Input("sdxl_height", default=1024, min=0, max=4096 * 4, optional=True),
-                io.Int.Input("sdxl_target_w", default=1024, min=0, max=4096 * 4, optional=True),
-                io.Int.Input("sdxl_target_h", default=1024, min=0, max=4096 * 4, optional=True),
-                io.Int.Input("sdxl_crop_w", default=0, min=0, max=4096 * 4, optional=True),
-                io.Int.Input("sdxl_crop_h", default=0, min=0, max=4096 * 4, optional=True),
-            ],
-            outputs=[io.Clip.Output()],
-        )
-
-    @classmethod
-    def execute(
-        cls,
-        clip,
-        mask_width=512,
-        mask_height=512,
-        sdxl_width=1024,
-        sdxl_height=1024,
-        sdxl_target_w=1024,
-        sdxl_target_h=1024,
-        sdxl_crop_w=0,
-        sdxl_crop_h=0,
-    ) -> io.NodeOutput:
-        settings = {
-            "mask_width": mask_width,
-            "mask_height": mask_height,
-            "sdxl_width": sdxl_width,
-            "sdxl_height": sdxl_height,
-            "sdxl_twidth": sdxl_target_w,
-            "sdxl_theight": sdxl_target_h,
-            "sdxl_cwidth": sdxl_crop_w,
-            "sdxl_cheight": sdxl_crop_h,
-        }
-        clip = clip.clone()
-        clip.patcher.model_options["x-promptcontrol.settings"] = settings
-        return io.NodeOutput(clip)
-
-
-class PCExtractScheduledPrompt(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCExtractScheduledPrompt",
-            display_name="PC: Show Prompt",
-            category="promptcontrol/tools",
-            description="Parses the input prompt and returns the prompt scheduled at the specified point",
-            inputs=[
-                io.String.Input("text", multiline=True),
-                io.Float.Input("at", min=0.0, max=1.0, default=1.0, step=0.01),
-                io.String.Input("tags", default="", optional=True),
-                io.Boolean.Input("expand_segs", default=False, optional=True),
-                io.Boolean.Input("expand_subs", default=False, optional=True),
-                io.Boolean.Input("expand_macros", default=False, optional=True),
-            ],
-            outputs=[io.String.Output()],
-            search_aliases=["extract scheduled prompt"],
-        )
-
-    @classmethod
-    def execute(cls, text, at, tags="", expand_segs=False, expand_subs=False, expand_macros=False) -> io.NodeOutput:
-        if expand_macros:
-            text = macroexpand(text)
-        schedule = parse_prompt_schedules(text, filters=tags)
-        _, entry = schedule.at_step(at)
-        prompt_text = entry.get("prompt", "")
-        if expand_segs:
-            prompt_text = segexpand(prompt_text, do_subs=expand_subs)
-        if expand_subs:
-            prompt_text = subexpand(prompt_text)
-        return io.NodeOutput(prompt_text)
-
-
-class PCMacroExpand(io.ComfyNode):
-    @classmethod
-    def define_schema(cls):
-        return io.Schema(
-            node_id="PCMacroExpand",
-            display_name="PC: Expand Macros",
-            category="promptcontrol/tools",
-            description="Expands DEF macros in a string and returns the result",
-            inputs=[
-                io.String.Input("text", multiline=True),
-            ],
-            outputs=[io.String.Output()],
-        )
-
-    @classmethod
-    def execute(cls, text) -> io.NodeOutput:
-        return io.NodeOutput(macroexpand(text))
-
-
-class PCLinkHelper(io.ComfyNode):
-    # a-z
-    NAMES = [chr(97 + i) for i in range(26)]
-
-    @classmethod
-    def define_schema(cls):
-        t1 = io.Autogrow.TemplateNames(io.AnyType.Input("link", raw_link=True), min=0, names=cls.NAMES)
-        t2 = io.Autogrow.TemplateNames(
-            io.AnyType.Input("value", lazy=True), min=0, names=[f"var{i + 1}" for i in range(50)]
-        )
-        return io.Schema(
-            node_id="PCNODELinkHelper",
-            display_name="PC: Extra argument helper for NODE",
-            category="promptcontrol/tools",
-            description="Takes in arbitrary inputs and renders them as NODE-compatible values, replacing $a -> $z with JSON link values.",
-            is_experimental=True,
-            inputs=[
-                io.Autogrow.Input("links", template=t1),
-                io.Autogrow.Input(
-                    "vars",
-                    template=t2,
-                ),
-                io.String.Input(
-                    "template",
-                    tooltip="The variables $a to $z will be replaced in this text with their corresponding input's JSON link value",
-                    placeholder="In this text you can refer to the input links as $a, $b etc. and the var inputs as either $var1 or $json1 etc. (the latter will be rendered through Python's json.dumps function which will cause strings to be quoted)",
-                    multiline=True,
-                ),
-            ],
-            outputs=[io.String.Output()],
-        )
-
-    # This requires https://github.com/Comfy-Org/ComfyUI/pull/15103 to work properly
-    # Without that PR, all inputs will be evaluated non-lazily
-    @classmethod
-    def check_lazy_status(cls, template, links, vars):
-        r = []
-        for name, (v, input_name) in vars.items():
-            if v is None and f"${name}" in template or v is None and f"$json{name[3:]}" in template:
-                r.append(input_name)
-        return r
-
-    @classmethod
-    def execute(cls, template, links, vars) -> io.NodeOutput:
-        text = template
-        for k in cls.NAMES:
-            v = "__EMPTY__"
-            if k in links:
-                # Replace : with \: to avoid breaking scheduling syntax when linking subgraphs. Any function that consumes this should replace \: with :
-                v = json.dumps(links[k]).replace(":", r"\:")
-            text = substitute_var(text, k, v)
-        for i in range(50):
-            v = "__EMPTY__"
-            k = f"var{i + 1}"
-            if k in vars:
-                v = vars[k]
-            text = substitute_var(text, k, str(v))
-            if f"$json{i + 1}" in text:
-                v = v if v == "__EMPTY__" else json.dumps(v)
-                text = substitute_var(text, f"json{i + 1}", v)
-
-        return io.NodeOutput(text)
-
-
-NODES = [
-    PCSetPCTextEncodeSettings,
-    PCAddMaskToCLIP,
-    PCAddMaskToCLIPMany,
-    PCSetLogLevel,
-    PCExtractScheduledPrompt,
-    PCMacroExpand,
-    PCLinkHelper,
-]

prompt_control/parser.py

@@ -1,397 +1,400 @@
-from __future__ import annotations
-
-import itertools as it
-from dataclasses import dataclass
+import lark
+import logging
 from math import ceil
-from typing import Any, TypeAlias
 
-from typing_extensions import override
+logging.basicConfig()
+log = logging.getLogger("comfyui-prompt-control-legacy")
 
-from .macros import expand_macros
-from .parsy import any_char, char_from, digit, eof, forward_declaration, generate, regex, seq, string, success
-
-FOREVER = float("inf")
-
-EvalResult: TypeAlias = tuple[float, str, list["LoRA"]]
+if lark.__version__ == "0.12.0":
+    x = "Your lark package reports an ancient version (0.12.0) and will not work. If you have the 'lark-parser' package in your Python environment, remove that and *reinstall* lark!"
+    log.error(x)
+    raise ImportError(x)
 
 
-def merge_until(i: EvalResult, minimum: float):
-    until, p, loras = i
-    until = min(until, minimum)
-    return until, p, loras
+prompt_parser = lark.Lark(
+    r"""
+!start: (prompt | /[][():|]/+)*
+prompt: (emphasized | embedding | scheduled | alternate | sequence | interpolate | loraspec | PLAIN | /</ | />/ | WHITESPACE)+
+!emphasized: "(" prompt? ")"
+        | "(" prompt ":" prompt ")"
+        | "[" prompt "]"
+scheduled: "[" [prompt ":"] [prompt] ":" _WS? NUMBER ["," NUMBER] "]"
+        | "[" [prompt ":"] [prompt] ":" _WS? TAG "]"
+sequence:  "[SEQ" ":" [prompt] ":" NUMBER (":" [prompt] ":" NUMBER)+ "]"
+interpolate.100: "[INT" ":" interp_prompts ":" interp_steps "]"
+interp_prompts: prompt (":" [prompt])+
+interp_steps: NUMBER ("," NUMBER)+ [":" NUMBER]
+alternate: "[" [prompt] ("|" [prompt])+ [":" NUMBER] "]"
+loraspec.99: "<lora:" FILENAME lora_weights [lora_block_weights] ">"
+lora_weights.1: (":" _WS? NUMBER)~1..2
+lora_block_weights.-1: ":" PLAIN
+embedding.100: "<emb:" FILENAME ">"
+WHITESPACE: /\s+/
+_WS: WHITESPACE
+PLAIN: /([^<>\\\[\]():|]|\\.)+/
+FILENAME: /[^<>:]+/
+TAG: /[A-Z_]+/
+%import common.SIGNED_NUMBER -> NUMBER
+""",
+    lexer="dynamic",
+)
+
+cut_parser = lark.Lark(
+    r"""
+!start: (prompt | /[][:()]/+)*
+prompt: (cut | PLAIN | WHITESPACE)+
+cut: "[CUT:" prompt ":" prompt [":" NUMBER  [ ":" NUMBER [":" NUMBER [ ":" PLAIN ] ] ] ]"]"
+WHITESPACE: /\s+/
+PLAIN: /([^\[\]:])+/
+%import common.SIGNED_NUMBER -> NUMBER
+"""
+)
 
 
-def batched(iterable, n, *, strict=False):
-    # batched('ABCDEFG', 2) → AB CD EF G
-    if n < 1:
-        raise ValueError("n must be at least one")
-    iterator = iter(iterable)
-    while batch := tuple(it.islice(iterator, n)):
-        if strict and len(batch) != n:
-            raise ValueError("batched(): incomplete batch")
-        yield batch
+class CutTransform(lark.Transformer):
+    def __default__(self, data, children, meta):
+        return children
+
+    def cut(self, args):
+        prompt, cutout, weight, strict_mask, start_from_masked, mask_token = args
+
+        return ("".join(flatten(prompt)), "".join(flatten(cutout)), weight, strict_mask, start_from_masked, mask_token)
+
+    def start(self, args):
+        prompt = []
+        cuts = []
+        for a in flatten(args):
+            if isinstance(a, str):
+                prompt.append(a)
+            else:
+                prompt.append(a[0])
+                cuts.append(a)
+        return "".join(prompt), cuts
+
+    def PLAIN(self, args):
+        return args
 
 
-EvalResult: TypeAlias = tuple[float, str, list["LoRA"]]
+def parse_cuts(text):
+    return CutTransform().transform(cut_parser.parse(text))
 
 
-class Expression:
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        return (FOREVER, "", [])
-
-    def required_steps(self, max_steps: float) -> set[float]:
-        return set()
-
-
-@dataclass
-class Text(Expression):
-    string: str
-
-    @override
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        assert isinstance(self.string, str)
-        return FOREVER, self.string, []
-
-
-@dataclass
-class Alternate(Expression):
-    prompts: list[Expression]
-    step: float = 0.1
-
-    @override
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        SCALE = 10_000
-        step = max(step, self.step)
-        position = (step * SCALE) / (self.step * SCALE)
-        idx = (ceil(position) - 1) % len(self.prompts)
-
-        r = self.prompts[max(0, idx)].eval(step, tags)
-        r = merge_until(r, max(self.step, ceil(position) * self.step))
-        return r
-
-    @override
-    def required_steps(self, max_steps: float):
-        r = set()
-        for x in self.prompts:
-            r.update(x.required_steps(max_steps))
-        r.update(set(x / 100 for x in range(0, int(max_steps * 100), int(self.step * 100))))
-        return r
-
-
-@dataclass
-class Sequence(Expression):
-    prompts: list[tuple[Expression, float]]
-
-    @override
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        item = Text("")
-        found_step = FOREVER
-        for prompt, switch_step in self.prompts:
-            if step <= switch_step:
-                found_step = switch_step
-                item = prompt
-                break
-
-        return merge_until(item.eval(step, tags), found_step)
-
-    @override
-    def required_steps(self, max_steps: float):
-        return set(step for _, step in self.prompts if step <= max_steps)
-
-
-@dataclass
-class Schedule(Expression):
-    before: Prompt
-    during: Prompt
-    after: Prompt
-    start: float
-    end: float
-    tag: str | None
-
-    def tag_matches(self, tags: list[str]):
-        return self.tag in tags
-
-    @override
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        if self.tag is not None and not self.tag_matches(tags):
-            return self.before.eval(step, tags)
-        if self.tag_matches(tags):
-            return self.during.eval(step, tags)
-
-        if step <= self.start:
-            return merge_until(self.before.eval(step, tags), self.start)
-        if self.start < step <= self.end:
-            return merge_until(self.during.eval(step, tags), self.end)
-        if step > self.end:
-            return self.after.eval(step, tags)
-        raise AssertionError("How are you here?")
-
-    @override
-    def required_steps(self, max_steps: float):
-        r = set()
-        if self.start < max_steps:
-            r.add(self.start)
-        if self.end < max_steps:
-            r.add(self.end)
-        r.update(self.before.required_steps(max_steps))
-        r.update(self.during.required_steps(max_steps))
-        r.update(self.after.required_steps(max_steps))
-        return r
-
-
-@dataclass
-class Prompt(Expression):
-    data: list[Expression]
-
-    @override
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        evals = [x.eval(step, tags) for x in self.data]
-        text = "".join(x[1] for x in evals)
-        untils = [x[0] for x in evals]
-        loras = []
-        for x in evals:
-            loras.extend(x[2])
-        until = FOREVER if not untils else min(untils)
-        return until, text, loras
-
-    @override
-    def required_steps(self, max_steps):
-        r = set()
-        for x in self.data:
-            r.update(x.required_steps(max_steps))
-        return r
-
-
-@dataclass
-class LoRA(Expression):
-    filename: str
-    w_model: float = 1.0
-    w_te: float = 1.0
-
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        return FOREVER, "", [self]
-
-
-def find_weight_at(weights: list[tuple[float, float]], step: float, until: float):
-    res_w = 0
-    for this, next in zip(weights, it.chain(weights[1:], [(0, FOREVER)]), strict=False):
-        w, start = this
-        _, next_start = next
-        if start > step or next_start < step:
-            until = min(until, start)
-            continue
-        res_w = w
-    return until, res_w
-
-
-@dataclass
-class LoRACTL(Expression):
-    filename: str
-    w_model: list[tuple[float, float]]
-    w_te: list[tuple[float, float]]
-
-    def eval(self, step: float, tags: list[str]) -> EvalResult:
-        until, w1 = find_weight_at(self.w_model, step, FOREVER)
-        until, w2 = find_weight_at(self.w_te, step, until)
-        lora = []
-        if w1 != 0 or w1 != 0:
-            lora = [LoRA(self.filename, w1, w2)]
-
-        return until, "", lora
-
-    def required_steps(self, max_steps):
-        r = set(x[1] for x in self.w_model)
-        r.update(set(x[1] for x in self.w_te))
-        return r
-
-
-def combine_arglist(prompts, start_end) -> Schedule:
-    a, b, c = prompts
-    start_or_tag, end = start_end
-    empty = Prompt([])
-    start = start_or_tag
-    # Handle [a:b:TAG]
-    if isinstance(start_or_tag, str):
-        if b is None:
-            before = empty
-            during = a  # [a:TAG] produces a when tag is active
-        else:
-            before, during = a, b  # [a:b:TAG] changes from a to b when tag is active
-        return Schedule(before, during, empty, start=0.0, end=FOREVER, tag=start_or_tag)
-    during = before = after = empty
-    if end is not None:
-        if b is None:  # [a:0,0.5] == [:a:0,0.5]
-            during = a
-            before = after = empty
-        elif c is None:  # [a:b:0,0.5]
-            before = empty
-            during = a
-            after = b
-        else:
-            before, during, after = a, b, c
+def flatten(x):
+    if type(x) in [str, tuple] or isinstance(x, dict) and "type" in x:
+        yield x
     else:
-        end = FOREVER
-        if b is None:  # [a:0.5] == [::a:0.5,0.5]
-            before = empty
-            during = a
-            after = a
-        else:
-            before = a
-            during = b
-            after = b
-            # c always gets ignored
-    start = float(start)  # for typechecking
-    return Schedule(before, during, after, start, end, tag=None)
+        for g in x:
+            yield from flatten(g)
 
 
-def token(s: str):
-    return string(s).map(Text)
+def clamp(a, b, c):
+    """clamp b between a and c"""
+    return min(max(a, b), c)
 
 
-def combine_prompt(*prompts):
-    p = prompts
-    if len(p) == 1:
-        p = p[0]
-    if isinstance(p, Prompt):
-        p = p.data[0] if len(p.data) == 1 else combine_prompt(*p.data)
-    if isinstance(p, Expression):
-        return p
-    p = [combine_prompt(x) for x in p]
-    return Prompt(p)
+def get_steps(tree):
+    res = [100]
+    interpolation_steps = []
+
+    def tostep(s):
+        w = float(s) * 100
+        w = int(clamp(0, w, 100))
+        return w
+
+    class CollectSteps(lark.Visitor):
+        def scheduled(self, tree):
+            i = tree.children[-1]
+            if i and i.type == "TAG":
+                return
+            for i in [-1, -2]:
+                if tree.children[i] is not None:
+                    tree.children[i] = tostep(tree.children[i])
+                    res.append(tree.children[i])
+
+        def interp_steps(self, tree):
+            tree.children[-1] = tostep(tree.children[-1] or 0.1)
+            for i, _ in enumerate(tree.children[:-1]):
+                tree.children[i] = tostep(tree.children[i])
+
+            interpolation_steps.append((tuple(tree.children[:-1]), tree.children[-1]))
+            res.extend(tree.children[:-1])
+
+        def sequence(self, tree):
+            steps = tree.children[1::2]
+            for i, steps in enumerate(steps):
+                w = float(tree.children[i * 2 + 1]) * 100
+                tree.children[i * 2 + 1] = clamp(0, w, 100)
+                res.append(w)
+
+        def alternate(self, tree):
+            step_size = int(round(float(tree.children[-1] or 0.1), 2) * 100)
+            step_size = clamp(1, step_size, 100)
+            tree.children[-1] = step_size
+            res.extend([x for x in range(step_size, 100, step_size)])
+
+    CollectSteps().visit(tree)
+
+    return sorted(set(interpolation_steps)), sorted(set(res))
 
 
-@dataclass
-class PromptSchedule:
-    parse_tree: Expression
-    filters: list[str]
-    start: float
-    end: float
-    num_steps: int
+def at_step(step, filters, tree):
+    class AtStep(lark.Transformer):
+        def scheduled(self, args):
+            when_end = None
+            before, after, when, *rest = args
+            if isinstance(when, str):
+                return before or "" if when not in filters else after or ""
 
-    def at_step(self, step: float) -> tuple[float, dict[str, Any]]:
-        max_step = self.num_steps or 1.0
-        if max_step > 1 and step < 1:
-            step = step * max_step
-        until, p, lora_list = self.parse_tree.eval(step, self.filters)
-        loras = {}
-        for lora in lora_list:
-            d = loras.get(lora.filename, {})
-            d["weight"] = d.get("weight", 0) + lora.w_model
-            d["weight_clip"] = d.get("weight_clip", 0) + lora.w_te
-            loras[lora.filename] = d
-        if max_step > 0 and until > 1:
-            # TODO: better logic for this?
-            until = min(until / max_step, 1.0)
-        return (min(max_step, round(until, 2)), {"prompt": p, "loras": loras})
+            if rest:
+                when_end = rest[0]
 
-    def with_filters(self, filters: str | None = None, start: float | None = None, end: float | None = None):
-        return PromptSchedule(
-            self.parse_tree,
-            self.filters if filters is None else parse_filters(filters),
-            self.start if start is None else start,
-            self.end if end is None else end,
-            self.num_steps,
-        )
+            if when_end is not None and step <= when and before is not None:
+                return ""
+
+            if when_end is not None and (step > when and step <= when_end):
+                # handle [a:0,1]
+                if before is None:
+                    return after or ""
+                return before or ""
+
+            if when_end is not None and step >= when_end:
+                # handle [a:0,1]
+                if before is None:
+                    return ""
+                return after or ""
+
+            if step <= when:
+                return before or ""
+            else:
+                return after or ""
+
+        def sequence(self, args):
+            previous_step = 0.0
+            prompts = args[::2]
+            steps = args[1::2]
+            for s, p in zip(steps, prompts):
+                if s >= step and step >= previous_step:
+                    previous_step = step
+                    return p or ""
+                else:
+                    previous_step = s
+            return ""
+
+        def interpolate(self, args):
+            prompts, starts = args
+            starts = starts[:-1]
+            prev_prompt = None
+            if step < starts[0]:
+                return prompts[0]
+            for i, x in enumerate(starts):
+                prev_prompt = prompts[i]
+                if x >= step:
+                    break
+            return prev_prompt
+
+        def interp_steps(self, args):
+            return list(args)
+
+        def interp_prompts(self, args):
+            return ["".join(flatten(a or [])) for a in args]
+
+        def alternate(self, args):
+            step_size = args[-1]
+            idx = ceil(step / step_size)
+            return args[(idx - 1) % (len(args) - 1)] or ""
+
+        def start(self, args):
+            prompt = []
+            loraspecs = {}
+            args = flatten(args)
+            for a in args:
+                if isinstance(a, str):
+                    prompt.append(a)
+                elif isinstance(a, tuple):
+                    # sum identical specs together
+                    n = a[0]
+                    # if clip weight is not provided, use unet weight
+                    w, w_clip = a[1][0], a[1][1 % len(a[1])]
+                    e = loraspecs.get(n, {})
+                    loraspecs[n] = {
+                        "weight": round(e.get("weight", 0.0) + w, 2),
+                        "weight_clip": round(e.get("weight_clip", 0.0) + w_clip, 2),
+                    }
+                    lbw = a[2]
+                    if lbw:
+                        loraspecs[n]["lbw"] = lbw
+                    if loraspecs[n]["weight"] == 0 and loraspecs[n]["weight_clip"] == 0 and not lbw:
+                        del loraspecs[n]
+                else:
+                    pass
+            p = "".join(prompt)
+            return {"prompt": p, "loras": loraspecs}
+
+        def PLAIN(self, args):
+            return args.replace("\\:", ":")
+
+        def FILENAME(self, value):
+            return str(value)
+
+        def embedding(self, args):
+            return "embedding:" + str(args[0])
+
+        def lora_weights(self, args):
+            return [float(str(a)) for a in args]
+
+        def lora_block_weights(self, args):
+            vals = args[0].split(";")
+            r = {}
+            for v in vals:
+                x = v.split("=", 2)
+                if len(x) != 2:
+                    continue
+                k, v = x[0].strip().upper(), x[1].strip()
+                r[k] = v
+            return r
+
+        def loraspec(self, args):
+            name = args[0]
+            params = args[1]
+            lbw = args[2]
+
+            return name, params, lbw
+
+        def __default__(self, data, children, meta):
+            for child in children:
+                yield child
+
+    return AtStep().transform(tree)
+
+
+class PromptSchedule(object):
+    def __init__(self, prompt, filters="", start=0.0, end=1.0, defaults=None, masks=None):
+        self.filters = filters
+        self.start = start
+        self.end = end
+        self.prompt = prompt.strip()
+        self.defaults = {}
+        if defaults:
+            self.defaults = defaults
+        self.loaded_loras = {}
+
+        self.interpolations = None
+        self.parsed_prompt = None
+        self.interpolations, self.parsed_prompt = self._parse()
+        self.masks = masks
+        if masks is None:
+            self.masks = []
+
+    def __iter__(self):
+        # Filter out zero, it's only useful for interpolation
+        return (x for x in self.parsed_prompt if x[0] != 0)
+
+    def _parse(self):
+        filters = [x.strip() for x in self.filters.upper().split(",")]
+        try:
+            parsed = []
+            interpolations = set()
+            tree = prompt_parser.parse(self.prompt)
+            interpolation_steps, steps = get_steps(tree)
+            log.debug("Interpolation steps: %s", interpolation_steps)
+
+            def f(x):
+                return round(x / 100, 2)
+
+            for t in steps:
+                p = at_step(t, filters, tree)
+                for control_points, step in interpolation_steps:
+                    interp_start = None
+                    interp_end = None
+                    if t == control_points[-1]:
+                        interp_start = max(control_points[0], int(self.start * 100))
+                        interp_end = min(control_points[-1], int(self.end * 100))
+                        control_points = tuple(
+                            sorted(set(f(c) for c in control_points if c >= interp_start or c <= interp_end))
+                        )
+                    if interp_start is not None and interp_end is not None and interp_end > interp_start:
+                        interpolations.add((control_points, f(step)))
+                parsed.append([f(t), p])
+
+        except lark.exceptions.LarkError as e:
+            log.error("Prompt editing parse error: %s", e)
+            parsed = [[1.0, {"prompt": self.prompt, "loras": {}}]]
+
+        # Tag filtering may return redundant prompts, so filter them out here
+        res = []
+        prev_p = None
+        prev_end = -1
+
+        for end_at, p in parsed:
+            # Preserve prompt if it ends at the start of an interpolation, otherwise bump its end time
+            if p == prev_p and res[-1][0] not in [x[0][0] for x in interpolations]:
+                res[-1][0] = end_at
+                continue
+            if end_at < self.start:
+                continue
+            elif end_at <= self.end:
+                res.append([end_at, p])
+                prev_end = end_at
+            elif end_at > self.end and prev_end < self.end:
+                res.append([end_at, p])
+                break
+            prev_p = p
+
+        # Always use the last prompt if everything was filtered
+        if len(res) == 0:
+            res = [[1.0, parsed[-1][1]]]
+
+        return interpolations, res
+
+    def add_masks(self, *masks):
+        for mask in masks:
+            if mask is not None:
+                self.masks.append(mask)
 
     def clone(self):
         return self.with_filters()
 
-    def __iter__(self):
-        return (x for x in self.parsed_prompt if x[0] != 0)
+    def with_filters(self, filters=None, start=None, end=None, defaults=None):
+        def ifspecified(x, defval):
+            return x if x is not None else defval
 
-    @property
-    def parsed_prompt(self):
-        max_step = self.num_steps or 1.0
-        required_steps = self.parse_tree.required_steps(max_step).union({max_step})
+        p = PromptSchedule(
+            self.prompt,
+            filters=ifspecified(filters, self.filters),
+            start=ifspecified(start, self.start),
+            end=ifspecified(end, self.end),
+            defaults=ifspecified(defaults, self.defaults),
+            masks=self.masks[:],
+        )
+        return p
 
-        prompts = list(sorted((self.at_step(step) for step in required_steps), key=lambda x: x[0]))
-        res = []
-        prev_end = -1
-        for end_at, p in prompts:
-            if end_at < self.start:
-                continue
-            elif end_at < self.end and prev_end < end_at:
-                res.append([end_at, p])
-                prev_end = end_at
-            elif end_at >= self.end and prev_end < self.end:
-                res.append([end_at, p])
-                break
+    def at_step(self, step, total_steps=1):
+        _, x = self.at_step_idx(step, total_steps)
+        return x
 
-        if len(res) == 0:
-            res = [[1.0], prompts[-1][1]]
+    def at_step_idx(self, step, total_steps=1):
+        for i, x in enumerate(self.parsed_prompt):
+            if x[0] * total_steps >= step:
+                return i, x
+        return len(self.parsed_prompt) - 1, self.parsed_prompt[-1]
 
-        return res
+    def interpolation_at(self, step, total_steps=1):
+        i, x = self.at_step_idx(step, total_steps)
+        for y in self.parsed_prompt[i:]:
+            step = min(y[0], 1.0)
+            if x[1]["prompt"] != y[1]["prompt"]:
+                return step, y
+        return 1.0, self.parsed_prompt[-1]
+
+    def load_loras(self, lora_cache=None):
+        from .utils import Timer, load_loras_from_schedule
+
+        if lora_cache is not None:
+            self.loaded_loras = lora_cache
+        with Timer("PromptSchedule.load_loras()"):
+            self.loaded_loras = load_loras_from_schedule(self.parsed_prompt, self.loaded_loras)
+        return self.loaded_loras
 
 
-def lora_weights(p):
-    @generate
-    def parser():
-        w_model = yield col >> p
-        w_te = yield (col >> p).optional(w_model)
-        return [w_model, w_te]
-
-    return parser.desc("lora_weights")
-
-
-prompt = forward_declaration()
-empty = Text("")
-comma = token(",")
-col = token(":")
-lsq = token("[")
-rsq = token("]")
-lpar = token("(")
-rpar = token(")")
-tag = regex(r"[A-Z_]+")
-non_special = regex(r"[^:\[\]()|\\<>#]+").map(Text)
-filename = regex(r"[^:<>]+")
-
-comment = string("#") >> any_char.until(eof | char_from("\n")) >> success(empty)
-escape = (string("\\") >> char_from("\\[]:#") | string(r"\(") | string(r"\)")).map(Text)
-emphasis = seq(lpar, (prompt | col).at_least(0), rpar)
-sign = string("+") | string("-")
-number = (
-    (sign.optional("") + (digit.many() + string(".") * 1 + digit.many() | digit.at_least(1)).concat())
-    .concat()
-    .map(float)
-)
-
-opt_prompt = prompt.optional(empty)
-step_range = seq(number | tag, (comma >> number).optional())
-arglist = seq((opt_prompt << col).optional() * 3, step_range)
-schedule = lsq >> arglist.combine(combine_arglist) << rsq
-
-alternate = (lsq >> seq(prompt.sep_by(string("|"), min=1), (col >> number).optional(0.1)) << rsq).combine(Alternate)
-sequence = (lsq >> string("SEQ") >> seq(col >> opt_prompt << col, number).at_least(1) << rsq).map(Sequence)
-bracketed = seq(lsq, prompt.at_least(0), rsq) | sequence | schedule | alternate
-lora = (string("<lora:") >> filename * 1 + lora_weights(number) << string(">")).combine(LoRA)
-ctlweight = seq(number, (string("@") >> number).optional(0)).sep_by(comma, min=1)
-loractl = (string("<loractl:") >> filename * 1 + lora_weights(ctlweight) << string(">")).combine(LoRACTL)
-emb = (string("<emb:") >> filename << string(">")).map(lambda f: Text(f"embedding:{f}"))
-
-expr = (
-    escape
-    | comment
-    | non_special
-    | bracketed
-    | emphasis.combine(combine_prompt)
-    | lora
-    | loractl
-    | emb
-    | char_from("<>").map(Text)
-)
-prompt_ = expr.at_least(1).combine(combine_prompt)
-prompt.become(prompt_)
-# Treat any character that isn't valid prompt syntax as just text
-all = (prompt | any_char.map(Text)).at_least(0).combine(combine_prompt)
-
-
-def parse_filters(filters: str):
-    return [x.strip().upper() for x in filters.split(",") if x.strip()]
-
-
-def parse(text):
-    return combine_prompt(all.parse(text))
-
-
-def parse_prompt_schedules(text, filters="", start=0, end=1.0, num_steps=0):
-    return PromptSchedule(parse(expand_macros(text.strip())), parse_filters(filters), start, end, num_steps)
+def parse_prompt_schedules(prompt):
+    return PromptSchedule(prompt)

prompt_control/parsy.py

@@ -1,720 +0,0 @@
-# Vendored from https://github.com/python-parsy/parsy/blob/master/src/parsy/__init__.py
-from __future__ import annotations
-
-import enum
-import operator
-import re
-from dataclasses import dataclass
-from functools import wraps
-from typing import Any, Callable, FrozenSet
-
-__version__ = "2.2"
-
-noop = lambda x: x
-
-
-def line_info_at(stream, index):
-    if index > len(stream):
-        raise ValueError("invalid index")
-    line = stream.count("\n", 0, index)
-    last_nl = stream.rfind("\n", 0, index)
-    col = index - (last_nl + 1)
-    return (line, col)
-
-
-class ParseError(RuntimeError):
-    def __init__(self, expected, stream, index):
-        self.expected = expected
-        self.stream = stream
-        self.index = index
-
-    def line_info(self) -> str:
-        try:
-            return "{}:{}".format(*line_info_at(self.stream, self.index))
-        except (TypeError, AttributeError):  # not a str
-            return str(self.index)
-
-    def __str__(self):
-        expected_list = sorted(repr(e) for e in self.expected)
-
-        if len(expected_list) == 1:
-            return f"expected {expected_list[0]} at {self.line_info()}"
-        else:
-            return f"expected one of {', '.join(expected_list)} at {self.line_info()}"
-
-
-@dataclass
-class Result:
-    status: bool
-    index: int
-    value: Any
-    furthest: int
-    expected: FrozenSet[str]
-
-    @staticmethod
-    def success(index, value) -> Result:
-        return Result(True, index, value, -1, frozenset())
-
-    @staticmethod
-    def failure(index, expected) -> Result:
-        return Result(False, -1, None, index, frozenset([expected]))
-
-    # collect the furthest failure from self and other
-    def aggregate(self, other) -> Result:
-        if not other:
-            return self
-
-        if self.furthest > other.furthest:
-            return self
-        elif self.furthest == other.furthest:
-            # if we both have the same failure index, we combine the expected messages.
-            return Result(self.status, self.index, self.value, self.furthest, self.expected | other.expected)
-        else:
-            return Result(self.status, self.index, self.value, other.furthest, other.expected)
-
-
-# Roughly, a stream is str|bytes|list, but in practice we are duck-typed
-# and could accept other things.
-# We should switch to this alias when all supported Python versions allow it:
-# type Stream = str | bytes | list
-
-
-class Parser:
-    """
-    A Parser is an object that wraps a function whose arguments are
-    a string to be parsed and the index on which to begin parsing.
-    The function should return either Result.success(next_index, value),
-    where the next index is where to continue the parse and the value is
-    the yielded value, or Result.failure(index, expected), where expected
-    is a string indicating what was expected, and the index is the index
-    of the failure.
-    """
-
-    def __init__(self, wrapped_fn: Callable[[str | bytes | list, int], Result]):
-        """
-        Creates a new Parser from a function that takes a stream
-        and returns a Result.
-        """
-        self.wrapped_fn = wrapped_fn
-
-    def __call__(self, stream: str | bytes | list, index: int) -> Any:
-        return self.wrapped_fn(stream, index)
-
-    def parse(self, stream: str | bytes | list) -> Any:
-        """Parses a string or list of tokens and returns the result or raise a ParseError."""
-        (result, _) = (self << eof).parse_partial(stream)
-        return result
-
-    def parse_partial(self, stream: str | bytes | list) -> tuple[Any, str | bytes | list]:
-        """
-        Parses the longest possible prefix of a given string.
-        Returns a tuple of the result and the unparsed remainder,
-        or raises ParseError
-        """
-        result = self(stream, 0)
-
-        if result.status:
-            return (result.value, stream[result.index :])
-        else:
-            raise ParseError(result.expected, stream, result.furthest)
-
-    def bind(self, bind_fn: Callable[[Any], Parser]) -> Parser:
-        @Parser
-        def bound_parser(stream: str | bytes | list, index: int) -> Result:
-            result = self(stream, index)
-
-            if result.status:
-                next_parser = bind_fn(result.value)
-                return next_parser(stream, result.index).aggregate(result)
-            else:
-                return result
-
-        return bound_parser
-
-    def map(self, map_function: Callable) -> Parser:
-        """
-        Returns a parser that transforms the produced value of the initial parser with map_function.
-        """
-        return self.bind(lambda res: success(map_function(res)))
-
-    def combine(self, combine_fn: Callable) -> Parser:
-        """
-        Returns a parser that transforms the produced values of the initial parser
-        with ``combine_fn``, passing the arguments using ``*args`` syntax.
-
-        The initial parser should return a list/sequence of parse results.
-        """
-        return self.bind(lambda res: success(combine_fn(*res)))
-
-    def combine_dict(self, combine_fn: Callable) -> Parser:
-        """
-        Returns a parser that transforms the value produced by the initial parser
-        using the supplied function/callable, passing the arguments using the
-        ``**kwargs`` syntax.
-
-        The value produced by the initial parser must be a mapping/dictionary from
-        names to values, or a list of two-tuples, or something else that can be
-        passed to the ``dict`` constructor.
-
-        If ``None`` is present as a key in the dictionary it will be removed
-        before passing to ``fn``, as will all keys starting with ``_``.
-        """
-        return self.bind(
-            lambda res: success(
-                combine_fn(
-                    **{
-                        k: v
-                        for k, v in dict(res).items()
-                        if k is not None and not (isinstance(k, str) and k.startswith("_"))
-                    }
-                )
-            )
-        )
-
-    def concat(self) -> Parser:
-        """
-        Returns a parser that concatenates together (as a string) the previously
-        produced values.
-        """
-        return self.map("".join)
-
-    def then(self, other: Parser) -> Parser:
-        """
-        Returns a parser which, if the initial parser succeeds, will
-        continue parsing with ``other``. This will produce the
-        value produced by ``other``.
-
-        """
-        return seq(self, other).combine(lambda left, right: right)
-
-    def skip(self, other: Parser) -> Parser:
-        """
-        Returns a parser which, if the initial parser succeeds, will
-        continue parsing with ``other``. It will produce the
-        value produced by the initial parser.
-        """
-        return seq(self, other).combine(lambda left, right: left)
-
-    def result(self, value: Any) -> Parser:
-        """
-        Returns a parser that, if the initial parser succeeds, always produces
-        the passed in ``value``.
-        """
-        return self >> success(value)
-
-    def many(self) -> Parser:
-        """
-        Returns a parser that expects the initial parser 0 or more times, and
-        produces a list of the results.
-        """
-        return self.times(0, float("inf"))
-
-    def times(self, min: int, max: int = None) -> Parser:
-        """
-        Returns a parser that expects the initial parser at least ``min`` times,
-        and at most ``max`` times, and produces a list of the results. If only one
-        argument is given, the parser is expected exactly that number of times.
-        """
-        if max is None:
-            max = min
-
-        @Parser
-        def times_parser(stream: str | bytes | list, index: int) -> Result:
-            values = []
-            times = 0
-            result = None
-
-            while times < max:
-                result = self(stream, index).aggregate(result)
-                if result.status:
-                    values.append(result.value)
-                    index = result.index
-                    times += 1
-                elif times >= min:
-                    break
-                else:
-                    return result
-
-            return Result.success(index, values).aggregate(result)
-
-        return times_parser
-
-    def at_most(self, n: int) -> Parser:
-        """
-        Returns a parser that expects the initial parser at most ``n`` times, and
-        produces a list of the results.
-        """
-        return self.times(0, n)
-
-    def at_least(self, n: int) -> Parser:
-        """
-        Returns a parser that expects the initial parser at least ``n`` times, and
-        produces a list of the results.
-        """
-        return self.times(n) + self.many()
-
-    def optional(self, default: Any = None) -> Parser:
-        """
-        Returns a parser that expects the initial parser zero or once, and maps
-        the result to a given default value in the case of no match. If no default
-        value is given, ``None`` is used.
-        """
-        return self.times(0, 1).map(lambda v: v[0] if v else default)
-
-    def until(self, other: Parser, min: int = 0, max: int = float("inf"), consume_other: bool = False) -> Parser:
-        """
-        Returns a parser that expects the initial parser followed by ``other``.
-        The initial parser is expected at least ``min`` times and at most ``max`` times.
-        By default, it does not consume ``other`` and it produces a list of the
-        results excluding ``other``. If ``consume_other`` is ``True`` then
-        ``other`` is consumed and its result is included in the list of results.
-        """
-
-        @Parser
-        def until_parser(stream: str | bytes | list, index: int) -> Result:
-            values = []
-            times = 0
-            while True:
-
-                # try parser first
-                res = other(stream, index)
-                if res.status and times >= min:
-                    if consume_other:
-                        # consume other
-                        values.append(res.value)
-                        index = res.index
-                    return Result.success(index, values)
-
-                # exceeded max?
-                if times >= max:
-                    # return failure, it matched parser more than max times
-                    return Result.failure(index, f"at most {max} items")
-
-                # failed, try parser
-                result = self(stream, index)
-                if result.status:
-                    # consume
-                    values.append(result.value)
-                    index = result.index
-                    times += 1
-                elif times >= min:
-                    # return failure, parser is not followed by other
-                    return Result.failure(index, "did not find other parser")
-                else:
-                    # return failure, it did not match parser at least min times
-                    return Result.failure(index, f"at least {min} items; got {times} item(s)")
-
-        return until_parser
-
-    def sep_by(self, sep: Parser, *, min: int = 0, max: int = float("inf")) -> Parser:
-        """
-        Returns a new parser that repeats the initial parser and
-        collects the results in a list. Between each item, the ``sep`` parser
-        is run (and its return value is discarded). By default it
-        repeats with no limit, but minimum and maximum values can be supplied.
-        """
-        zero_times = success([])
-        if max == 0:
-            return zero_times
-        res = self.times(1) + (sep >> self).times(min - 1, max - 1)
-        if min == 0:
-            res |= zero_times
-        return res
-
-    def desc(self, description: str) -> Parser:
-        """
-        Returns a new parser with a description added, which is used in the error message
-        if parsing fails.
-        """
-
-        @Parser
-        def desc_parser(stream: str | bytes | list, index: int) -> Result:
-            result = self(stream, index)
-            if result.status:
-                return result
-            else:
-                return Result.failure(index, description)
-
-        return desc_parser
-
-    def mark(self) -> Parser:
-        """
-        Returns a parser that wraps the initial parser's result in a value
-        containing column and line information of the match, as well as the
-        original value. The new value is a 3-tuple:
-
-        ((start_row, start_column),
-         original_value,
-         (end_row, end_column))
-        """
-
-        @generate
-        def marked():
-            start = yield line_info
-            body = yield self
-            end = yield line_info
-            return (start, body, end)
-
-        return marked
-
-    def tag(self, name: str) -> Parser:
-        """
-        Returns a parser that wraps the produced value of the initial parser in a
-        2 tuple containing ``(name, value)``. This provides a very simple way to
-        label parsed components
-        """
-        return self.map(lambda v: (name, v))
-
-    def should_fail(self, description: str) -> Parser:
-        """
-        Returns a parser that fails when the initial parser succeeds, and succeeds
-        when the initial parser fails (consuming no input). A description must
-        be passed which is used in parse failure messages.
-
-        This is essentially a negative lookahead
-        """
-
-        @Parser
-        def fail_parser(stream: str | bytes | list, index: int) -> Result:
-            res = self(stream, index)
-            if res.status:
-                return Result.failure(index, description)
-            return Result.success(index, res)
-
-        return fail_parser
-
-    def __add__(self, other: Parser) -> Parser:
-        return seq(self, other).combine(operator.add)
-
-    def __mul__(self, other: int | range) -> Parser:
-        if isinstance(other, range):
-            return self.times(other.start, other.stop - 1)
-        return self.times(other)
-
-    def __or__(self, other: Parser) -> Parser:
-        return alt(self, other)
-
-    # haskelley operators, for fun #
-
-    # >>
-    def __rshift__(self, other: Parser) -> Parser:
-        return self.then(other)
-
-    # <<
-    def __lshift__(self, other: Parser) -> Parser:
-        return self.skip(other)
-
-
-def alt(*parsers: Parser) -> Parser:
-    """
-    Creates a parser from the passed in argument list of alternative
-    parsers, which are tried in order, moving to the next one if the
-    current one fails.
-    """
-    if not parsers:
-        return fail("<empty alt>")
-
-    @Parser
-    def alt_parser(stream: str | bytes | list, index: int) -> Result:
-        result = None
-        for parser in parsers:
-            result = parser(stream, index).aggregate(result)
-            if result.status:
-                return result
-
-        return result
-
-    return alt_parser
-
-
-def seq(*parsers: Parser, **kw_parsers: Parser) -> Parser:
-    """
-    Takes a list of parsers, runs them in order,
-    and collects their individuals results in a list,
-    or in a dictionary if you pass them as keyword arguments.
-    """
-    if not parsers and not kw_parsers:
-        return success([])
-
-    if parsers and kw_parsers:
-        raise ValueError("Use either positional arguments or keyword arguments with seq, not both")
-
-    if parsers:
-
-        @Parser
-        def seq_parser(stream: str | bytes | list, index: int) -> Result:
-            result = None
-            values = []
-            for parser in parsers:
-                result = parser(stream, index).aggregate(result)
-                if not result.status:
-                    return result
-                index = result.index
-                values.append(result.value)
-            return Result.success(index, values).aggregate(result)
-
-        return seq_parser
-    else:
-
-        @Parser
-        def seq_kwarg_parser(stream: str | bytes | list, index: int) -> Result:
-            result = None
-            values = {}
-            for name, parser in kw_parsers.items():
-                result = parser(stream, index).aggregate(result)
-                if not result.status:
-                    return result
-                index = result.index
-                values[name] = result.value
-            return Result.success(index, values).aggregate(result)
-
-        return seq_kwarg_parser
-
-
-def generate(fn) -> Parser:
-    """
-    Creates a parser from a generator function
-    """
-    if isinstance(fn, str):
-        return lambda f: generate(f).desc(fn)
-
-    @Parser
-    @wraps(fn)
-    def generated(stream: str | bytes | list, index: int) -> Result:
-        # start up the generator
-        iterator = fn()
-
-        result = None
-        value = None
-        try:
-            while True:
-                next_parser = iterator.send(value)
-                result = next_parser(stream, index).aggregate(result)
-                if not result.status:
-                    return result
-                value = result.value
-                index = result.index
-        except StopIteration as stop:
-            returnVal = stop.value
-            if isinstance(returnVal, Parser):
-                return returnVal(stream, index).aggregate(result)
-
-            return Result.success(index, returnVal).aggregate(result)
-
-    return generated
-
-
-index = Parser(lambda _, index: Result.success(index, index))
-line_info = Parser(lambda stream, index: Result.success(index, line_info_at(stream, index)))
-
-
-def success(value: Any) -> Parser:
-    """
-    Returns a parser that does not consume any of the stream, but
-    produces ``value``.
-    """
-    return Parser(lambda _, index: Result.success(index, value))
-
-
-def fail(expected: str) -> Parser:
-    """
-    Returns a parser that always fails with the provided error message.
-    """
-    return Parser(lambda _, index: Result.failure(index, expected))
-
-
-def string(expected_string: str, transform: Callable[[str], str] = noop) -> Parser:
-    """
-    Returns a parser that expects the ``expected_string`` and produces
-    that string value.
-
-    Optionally, a transform function can be passed, which will be used on both
-    the expected string and tested string.
-    """
-
-    slen = len(expected_string)
-    transformed_s = transform(expected_string)
-
-    @Parser
-    def string_parser(stream: str, index: int) -> Result:
-        if transform(stream[index : index + slen]) == transformed_s:
-            return Result.success(index + slen, expected_string)
-        else:
-            return Result.failure(index, expected_string)
-
-    return string_parser
-
-
-def regex(exp: str, flags=0, group: int | str | tuple = 0) -> Parser:
-    """
-    Returns a parser that expects the given ``exp``, and produces the
-    matched string. ``exp`` can be a compiled regular expression, or a
-    string which will be compiled with the given ``flags``.
-
-    Optionally, accepts ``group``, which is passed to re.Match.group
-    https://docs.python.org/3/library/re.html#re.Match.group> to
-    return the text from a capturing group in the regex instead of the
-    entire match.
-    """
-
-    if isinstance(exp, (str, bytes)):
-        exp = re.compile(exp, flags)
-    if isinstance(group, (str, int)):
-        group = (group,)
-
-    @Parser
-    def regex_parser(stream: str | bytes | list, index: int) -> Result:
-        match = exp.match(stream, index)
-        if match:
-            return Result.success(match.end(), match.group(*group))
-        else:
-            return Result.failure(index, exp.pattern)
-
-    return regex_parser
-
-
-def test_item(func: Callable[..., bool], description: str) -> Parser:
-    """
-    Returns a parser that tests a single item from the list of items being
-    consumed, using the callable ``func``. If ``func`` returns ``True``, the
-    parse succeeds, otherwise the parse fails with the description
-    ``description``.
-    """
-
-    @Parser
-    def test_item_parser(stream: str | bytes | list, index: int) -> Result:
-        if index < len(stream):
-            if isinstance(stream, bytes):
-                # Subscripting bytes with `[index]` instead of
-                # `[index:index + 1]` returns an int
-                item = stream[index : index + 1]
-            else:
-                item = stream[index]
-            if func(item):
-                return Result.success(index + 1, item)
-        return Result.failure(index, description)
-
-    return test_item_parser
-
-
-def test_char(func: Callable[..., bool], description: str) -> Parser:
-    """
-    Returns a parser that tests a single character with the callable
-    ``func``. If ``func`` returns ``True``, the parse succeeds, otherwise
-    the parse fails with the description ``description``.
-    """
-    # Implementation is identical to test_item
-    return test_item(func, description)
-
-
-def match_item(item: Any, description: str = None) -> Parser:
-    """
-    Returns a parser that tests the next item (or character) from the stream (or
-    string) for equality against the provided item. Optionally a string
-    description can be passed.
-    """
-
-    if description is None:
-        description = str(item)
-    return test_item(lambda i: item == i, description)
-
-
-def string_from(*strings: str, transform: Callable[[str], str] = noop):
-    """
-    Accepts a sequence of strings as positional arguments, and returns a parser
-    that matches and returns one string from the list. The list is first sorted
-    in descending length order, so that overlapping strings are handled correctly
-    by checking the longest one first.
-    """
-    # Sort longest first, so that overlapping options work correctly
-    return alt(*(string(s, transform) for s in sorted(strings, key=len, reverse=True)))
-
-
-def char_from(string: str | bytes) -> Parser:
-    """
-    Accepts a string and returns a parser that matches and returns one character
-    from the string.
-    """
-    if isinstance(string, bytes):
-        return test_char(lambda c: c in string, b"[" + string + b"]")
-    else:
-        return test_char(lambda c: c in string, "[" + string + "]")
-
-
-def peek(parser: Parser) -> Parser:
-    """
-    Returns a lookahead parser that parses the input stream without consuming
-    chars.
-    """
-
-    @Parser
-    def peek_parser(stream: str | bytes | list, index: int) -> Result:
-        result = parser(stream, index)
-        if result.status:
-            return Result.success(index, result.value)
-        else:
-            return result
-
-    return peek_parser
-
-
-any_char = test_char(lambda c: True, "any character")
-
-whitespace = regex(r"\s+")
-
-letter = test_char(lambda c: c.isalpha(), "a letter")
-
-digit = test_char(lambda c: c.isdigit(), "a digit")
-
-decimal_digit = char_from("0123456789")
-
-
-@Parser
-def eof(stream: str | bytes | list, index: int) -> Result:
-    """
-    A parser that only succeeds if the end of the stream has been reached.
-    """
-
-    if index >= len(stream):
-        return Result.success(index, None)
-    else:
-        return Result.failure(index, "EOF")
-
-
-def from_enum(enum_cls: type[enum.Enum], transform=noop) -> Parser:
-    """
-    Given a class that is an enum.Enum class
-    https://docs.python.org/3/library/enum.html , returns a parser that
-    will parse the values (or the string representations of the values)
-    and return the corresponding enum item.
-    """
-
-    items = sorted(
-        ((str(enum_item.value), enum_item) for enum_item in enum_cls), key=lambda t: len(t[0]), reverse=True
-    )
-    return alt(*(string(value, transform=transform).result(enum_item) for value, enum_item in items))
-
-
-class forward_declaration(Parser):
-    """
-    An empty parser that can be used as a forward declaration,
-    especially for parsers that need to be defined recursively.
-
-    You must use `.become(parser)` before using.
-    """
-
-    def __init__(self):
-        pass
-
-    def _raise_error(self, *args, **kwargs):
-        raise ValueError("You must use 'become' before attempting to call `parse` or `parse_partial`")
-
-    parse = _raise_error
-    parse_partial = _raise_error
-
-    def become(self, other: Parser):
-        """
-        Take on the behavior of the given parser.
-        """
-        self.__dict__ = other.__dict__
-        self.__class__ = other.__class__

prompt_control/prompts.py

@@ -1,651 +0,0 @@
-from __future__ import annotations
-
-import logging
-import math
-import re
-from collections import defaultdict
-from functools import partial
-from typing import Any
-
-import torch
-from comfy_extras.nodes_mask import FeatherMask, MaskComposite
-from nodes import ConditioningAverage
-
-from .adv_encode import advanced_encode_from_tokens
-from .attention_couple_ppm import set_cond_attnmask
-from .cutoff import process_cuts
-from .cutoff_parser import parse_cuts
-from .utils import (
-    ComfyConditioning,
-    FunctionSpec,
-    call_node,
-    get_function,
-    parse_floats,
-    safe_float,
-    smarter_split,
-    split_by_function,
-    split_quotable,
-)
-
-log = logging.getLogger("comfyui-prompt-control")
-
-AVAILABLE_STYLES = ["comfy", "perp", "A1111", "compel", "comfy++", "down_weight"]
-AVAILABLE_NORMALIZATIONS = ["none", "mean", "length", "length+mean"]
-
-SHUFFLE_GEN = torch.Generator(device="cpu")
-
-
-def get_sdxl(text: str, defaults: dict[str, Any]) -> tuple[str, dict[str, int]]:
-    # Defaults fail to parse and get looked up from the defaults dict
-    text, sdxl = get_function(text, "SDXL", ["none", "none", "none"])
-    if not sdxl:
-        return text, {}
-    args = sdxl[0].args
-    d = defaults
-    w, h = parse_floats(args[0], [d.get("sdxl_width", 1024), d.get("sdxl_height", 1024)], split_re="\\s+")
-    tw, th = parse_floats(args[1], [d.get("sdxl_twidth", 1024), d.get("sdxl_theight", 1024)], split_re="\\s+")
-    cropw, croph = parse_floats(args[2], [d.get("sdxl_cwidth", 0), d.get("sdxl_cheight", 0)], split_re="\\s+")
-
-    opts = {
-        "width": int(w),
-        "height": int(h),
-        "target_width": int(tw),
-        "target_height": int(th),
-        "crop_w": int(cropw),
-        "crop_h": int(croph),
-    }
-    return text, opts
-
-
-def get_clipweights(text: str, existing_spec: dict[str, float] | None = None) -> tuple[dict[str, float], str]:
-    text, spec = get_function(text, "TE_WEIGHT", defaults=None)
-    if not spec:
-        return existing_spec or {}, text
-    args = spec[0].args[0].strip()
-    res = {}
-    for arg in args.split(","):
-        try:
-            te, val = arg.strip().split("=")
-            te, val = te.strip(), float(val.strip())
-            res[te] = val
-        except ValueError:
-            log.warning("Invalid TE weight spec '%s', ignoring...", arg.strip())
-    return res, text
-
-
-def get_style(text: str, default_style="comfy", default_normalization="none") -> tuple[str, str, str]:
-    text, styles = get_function(text, "STYLE", [default_style, default_normalization])
-    if not styles:
-        return default_style, default_normalization, text
-    style, normalization = styles[0].args
-    style = style.strip()
-    normalization = normalization.strip()
-    if style.replace("old+", "") not in AVAILABLE_STYLES:
-        log.warning("Unrecognized prompt style: %s. Using %s", style, default_style)
-
-    for part in normalization.split("+"):
-        if part not in AVAILABLE_NORMALIZATIONS:
-            log.warning("Unrecognized prompt normalization: %s. Using %s", normalization, default_normalization)
-            normalization = default_normalization
-            break
-
-    return style, normalization, text
-
-
-def shuffle_chunk(func_spec: FunctionSpec, c: str) -> str:
-    func = func_spec.name
-    shuffle = func_spec.args
-    shuffle_count = int(safe_float(shuffle[0], 0))
-    _, separator, joiner = shuffle
-    if separator == "default":
-        separator = ","
-
-    if not separator:
-        separator = ","
-
-    joiner = {
-        "default": ",",
-        "separator": separator,
-    }.get(joiner, joiner)
-
-    log.debug("%s arg=%s sep=%s join=%s", func, shuffle_count, separator, joiner)
-    separated = smarter_split(separator, c)
-    log.debug("Prompt split into %s", separated)
-    if func == "SHIFT":
-        shuffle_count = shuffle_count % len(separated)
-        permutation = separated[shuffle_count:] + separated[:shuffle_count]
-    elif func == "SHUFFLE":
-        SHUFFLE_GEN.manual_seed(shuffle_count)
-        permutation = [separated[i] for i in torch.randperm(len(separated), generator=SHUFFLE_GEN)]
-    else:
-        # ??? should never get here
-        permutation = separated
-
-    permutation = [p for p in permutation if p.strip()]
-    if permutation != separated:
-        c = joiner.join(permutation)
-    return c
-
-
-def fix_word_ids(tokens):
-    """Fix word indexes. Tokenizing separately (when BREAKs exist) causes the indexes
-    to restart which causes problems with some weighting algorithms that rely on them"""
-    for key in tokens:
-        max_idx = 0
-        for group in range(len(tokens[key])):
-            for i, token in enumerate(tokens[key][group]):
-                if len(token) < 3:
-                    # No need to fix ids when they don't exist
-                    return tokens
-                # Ignore zeros, they represent the padding token
-                if token[2] != 0 and token[2] < max_idx:
-                    tokens[key][group][i] = (token[0], token[1], token[2] + max_idx)
-            max_idx = max(max_idx, max(x for _, _, x in tokens[key][group]))
-    return tokens
-
-
-def tokenize_chunks(clip, text, need_word_ids, can_break):
-    chunks = list(split_quotable(text, r"\bBREAK\b"))
-    token_chunks = []
-    shuffled_chunks = []
-    for c in chunks:
-        c, shuffles = get_function(c.strip(), "(SHIFT|SHUFFLE)", ["0", "default", "default"])
-        r = c
-        for s in shuffles:
-            r = shuffle_chunk(s, r)
-        if r != c:
-            log.info("Shuffled prompt chunk to %s", r)
-        shuffled_chunks.append(r)
-        t = clip.tokenize(c, return_word_ids=need_word_ids)
-        token_chunks.append(t)
-
-    tokens = token_chunks[0]
-    full_prompt = "".join(shuffled_chunks)
-    full_tokenized = tokens
-    if len(chunks) > 1:
-        full_tokenized = clip.tokenize(full_prompt, return_word_ids=need_word_ids)
-        for key in tokens:
-            if not can_break.get(key):
-                log.warning("BREAK does not make sense for %s, tokenizing as one chunk. Use CAT instead.", key)
-                tokens[key] = full_tokenized[key]
-                continue
-            for c in token_chunks[1:]:
-                tokens[key].extend(c[key])
-
-    return tokens
-
-
-def tokenize(clip, text, can_break, empty_tokens):
-    # defaults=None means there is no argument parsing at all
-    text, l_prompts = get_function(text, "CLIP_L", defaults=None)
-    text, te_prompts = get_function(text, "TE", defaults=None)
-    need_word_ids = True
-    tokens = tokenize_chunks(clip, text, need_word_ids, can_break)
-
-    per_te_prompts = defaultdict(list)
-    if l_prompts:
-        log.warning("Note: CLIP_L is deprecated. Use TE(l=prompt) instead")
-        per_te_prompts["l"] = [x.args for x in l_prompts]
-
-    for prompt in te_prompts:
-        prompt = prompt.args[0]
-        if prompt.strip() == "help":
-            log.info("Encoders available for TE: %s", ", ".join(tokens.keys()))
-            continue
-        params = prompt.split("=", 1)
-        if len(params) != 2:
-            log.warning("Invalid TE call, ignoring: %s", prompt)
-            continue
-        te = params[0].strip()
-        prompt = params[1].strip()
-        if te not in tokens:
-            log.warning("Invalid TE call, no TE with key '%s', ignoring: %s", te)
-            log.info("Encoders available for TE: %s", ", ".join(tokens.keys()))
-            continue
-        per_te_prompts[te].append(prompt)
-
-    if per_te_prompts:
-        for key in per_te_prompts:
-            prompt = " ".join(per_te_prompts[key])
-            tokens[key] = tokenize_chunks(clip, prompt, need_word_ids, can_break)[key]
-            log.info("Encoded prompt with TE '%s': %s", key, prompt)
-
-    maxlen = max([0] + [len(tokens[k]) for k in tokens if can_break[k]])
-    for k in tokens:
-        if not can_break[k]:
-            continue
-        while len(tokens[k]) < maxlen:
-            tokens[k] += empty_tokens[k]
-
-    return fix_word_ids(tokens)
-
-
-def encode_prompt_segment(
-    clip,
-    text,
-    settings,
-    default_style="comfy",
-    default_normalization="none",
-    clip_weights=None,
-) -> list[ComfyConditioning]:
-    style, normalization, text = get_style(text, default_style, default_normalization)
-    clip_weights, text = get_clipweights(text, clip_weights)
-    text, cuts = parse_cuts(text)
-    extra = {}
-    if clip_weights:
-        extra["clip_weights"] = clip_weights
-    if cuts:
-        extra["cuts"] = cuts
-
-    empty = clip.tokenize("", return_word_ids=True)
-    can_break = {}
-    for k in empty:
-        tokenizer = getattr(clip.tokenizer, f"clip_{k}", getattr(clip.tokenizer, k, None))
-        can_break[k] = tokenizer and getattr(tokenizer, "pad_to_max_length", False)
-
-    clip = hook_te(clip, empty.keys(), style, normalization, extra)
-
-    # Chunks to ConditioningAverage:
-
-    text, averages = split_by_function(text, "AVG", ["0.5"], require_args=False)
-    prompts_to_avg = []
-    for chunk, avg in averages:
-        w = safe_float(avg.args[0], 0.5)
-        prompts_to_avg.append((text, w))
-        text = chunk
-    prompts_to_avg.append((text, 1.0))
-
-    conds_to_avg = []
-    for prompt, weight in prompts_to_avg:
-        conds_to_cat = []
-        for c in split_quotable(prompt, r"\bCAT\b"):
-            tokens = tokenize(clip, c, can_break, empty)
-            conds_to_cat.append(clip.encode_from_tokens_scheduled(tokens, add_dict=settings))
-
-        base = conds_to_cat[0]
-        for cond in conds_to_cat[1:]:
-            assert len(cond) == len(base), "Conditioning length mismatch"
-            # Pooled gets ignored
-            for i in range(len(base)):
-                c1 = base[i][0]
-                c2 = cond[i][0]
-                base[i][0] = torch.cat((c1, c2), 1)
-        conds_to_avg.append((base, weight))
-
-    base, w = conds_to_avg[0]
-    for cond, next_w in conds_to_avg[1:]:
-        assert len(base) == len(cond), "Conditioning length mismatch"
-        if w == 1.0:
-            w = next_w
-            continue
-        for i in range(len(base)):
-            (cond,) = call_node(ConditioningAverage, [base[i]], [cond[i]], w)
-            base[i] = cond[0]
-        w = next_w
-
-    return base
-
-
-def calc_w(tensor, w):
-    if math.isclose(w, 0):
-        return torch.zeros_like(tensor)
-    elif math.isclose(w, 1.0):
-        return tensor
-    else:
-        return tensor * w
-
-
-def apply_weights(output, te_name, spec):
-    """Applies weights to TE outputs"""
-    if not spec:
-        return output
-
-    if te_name.startswith("clip_"):
-        te_name = te_name[5:]
-
-    default = spec.get("all", None)
-
-    if isinstance(output, tuple):
-        out, pooled, *extra = output
-        pkey = te_name + "_pooled"
-        if te_name in spec or pkey in spec or default is not None:
-            w = spec.get(te_name, default)
-            pooled_w = spec.get(pkey, w)
-            if w is None:
-                w = 1.0
-            if pooled_w is None:
-                pooled_w = 1.0
-            log.info("Weighting %s output by %s, pooled by %s", te_name, w, pooled_w)
-            out = calc_w(out, w)
-            if pooled is not None:
-                pooled = calc_w(pooled, pooled_w)
-
-        return (out, pooled) + tuple(extra)
-    else:
-        if te_name in spec or default is not None:
-            w = spec.get(te_name, default)
-            log.info("Weighting %s output by %s", te_name, w)
-            output = calc_w(output, w)
-        return output
-
-
-def make_patch(te_name, orig_fn, normalization, style, extra):
-    def encode(t):
-        r = advanced_encode_from_tokens(
-            t, normalization, style, orig_fn, return_pooled=True, apply_to_pooled=False, **extra
-        )
-        return apply_weights(r, te_name, extra.get("clip_weights"))
-
-    if "cuts" in extra:
-        return partial(process_cuts, encode, extra)
-    return encode
-
-
-def hook_te(clip, te_names, style, normalization, extra):
-    if style == "comfy" and normalization == "none" and not extra:
-        return clip
-    newclip = clip.clone()
-    for te_name in te_names:
-        tokenizer = getattr(clip.tokenizer, f"clip_{te_name}", getattr(clip.tokenizer, te_name, None))
-        if tokenizer:
-            x = extra.copy()
-            x["tokenizer"] = tokenizer
-            if not hasattr(clip.patcher.model, te_name):
-                te_name = "clip_" + te_name
-            if not hasattr(clip.patcher.model, te_name):
-                log.warning("TE model %s not found on model patcher. Skipping...", te_name)
-                continue
-
-            log.debug("Hooked into te=%s with style=%s, normalization=%s", te_name, style, normalization)
-            encode = clip.patcher.get_model_object(f"{te_name}.encode_token_weights")
-            x["has_negpip"] = clip.patcher.model_options.get("ppm_negpip", False)
-            newclip.patcher.add_object_patch(
-                f"{te_name}.encode_token_weights",
-                make_patch(
-                    te_name,
-                    encode,
-                    normalization,
-                    style,
-                    x,
-                ),
-            )
-        # 'g' and 'l' exist in these are clip_g and clip_l
-        else:
-            log.warning("Tokens contain items with key %s but no tokenizer found on object with that name.", te_name)
-    return newclip
-
-
-def get_area(text):
-    text, areas = get_function(text, "AREA", ["0 1", "0 1", "1"])
-    if not areas:
-        return text, None
-
-    args = areas[0].args
-    x, w = parse_floats(args[0], [0.0, 1.0], split_re="\\s+")
-    y, h = parse_floats(args[1], [0.0, 1.0], split_re="\\s+")
-    weight = safe_float(args[2], 1.0)
-
-    def is_pct(f):
-        return f >= 0.0 and f <= 1.0
-
-    def is_pixel(f):
-        return f == 0 or f > 1
-
-    if all(is_pct(v) for v in [h, w, y, x]):
-        area = ("percentage", h, w, y, x)
-    elif all(is_pixel(v) for v in [h, w, y, x]):
-        area = (int(h) // 8, int(w) // 8, int(y) // 8, int(x) // 8)
-    else:
-        raise Exception(
-            f"AREA specified with invalid size {x} {w}, {h} {y}. They must either all"
-            " be percentages between 0 and 1 or positive integer pixel values excluding 1"
-        )
-
-    return text, (area, weight)
-
-
-def get_mask_size(text, defaults):
-    text, sizes = get_function(text, "MASK_SIZE", ["512", "512"])
-    if not sizes:
-        return text, (defaults.get("mask_width", 512), defaults.get("mask_height", 512))
-    w, h = sizes[0].args
-    return text, (int(w), int(h))
-
-
-def make_mask(args, size, weight):
-    x1, x2 = parse_floats(args[0], [0.0, 1.0], split_re="\\s+")
-    y1, y2 = parse_floats(args[1], [0.0, 1.0], split_re="\\s+")
-
-    def is_pct(f):
-        return f >= 0.0 and f <= 1.0
-
-    def is_pixel(f):
-        return f == 0 or f > 1
-
-    if all(is_pct(v) for v in [x1, x2, y1, y2]):
-        w, h = size
-        xs = int(w * x1), int(w * x2)
-        ys = int(h * y1), int(h * y2)
-    elif all(is_pixel(v) for v in [x1, x2, y1, y2]):
-        w, h = size
-        xs = int(x1), int(x2)
-        ys = int(y1), int(y2)
-    else:
-        raise Exception(
-            f"MASK specified with invalid size {x1} {x2}, {y1} {y2}. They must either all"
-            " be percentages between 0 and 1 or positive integer pixel values excluding 1"
-        )
-
-    mask = torch.full((h, w), 0, dtype=torch.float32, device="cpu")
-    mask[ys[0] : ys[1], xs[0] : xs[1]] = weight
-    mask = mask.unsqueeze(0)
-    log.debug("Mask xs=%s, ys=%s, shape=%s, weight=%s", xs, ys, mask.shape, weight)
-    return mask
-
-
-def get_mask(text, size, input_masks):
-    """Parse MASK(x1 x2, y1 y2, weight), IMASK(i, weight) and FEATHER(left top right bottom)"""
-    # TODO: combine multiple masks
-    text, masks = get_function(text, "MASK", ["0 1", "0 1", "1", "multiply"])
-    text, imasks = get_function(text, "IMASK", ["0", "1", "multiply"])
-    text, feathers = get_function(text, "FEATHER", ["0 0 0 0"])
-    text, maskw = get_function(text, "MASKW", ["1.0"])
-    if not masks and not imasks:
-        return text, None, None
-
-    def feather(f, mask):
-        left, top, right, bottom, *_ = [int(x) for x in parse_floats(f[0], [0, 0, 0, 0], split_re="\\s+")]
-        mask = call_node(FeatherMask, mask, left, top, right, bottom)[0]
-        log.info("FeatherMask l=%s, t=%s, r=%s, b=%s", left, top, right, bottom)
-        return mask
-
-    mask = None
-    totalweight = 1.0
-    if maskw:
-        totalweight = safe_float(maskw[0].args[0], 1.0)
-    i = 0
-    for m in masks:
-        weight = safe_float(m.args[2], 1.0)
-        op = m.args[3]
-        nextmask = make_mask(m.args, size, weight)
-        if i < len(feathers):
-            nextmask = feather(feathers[i].args, nextmask)
-        i += 1
-        if mask is not None:
-            log.info("MaskComposite op=%s", op)
-            mask = call_node(MaskComposite, mask, nextmask, 0, 0, op)[0]
-        else:
-            mask = nextmask
-
-    for im in imasks:
-        idx, w, op = im.args
-        idx = int(safe_float(idx, 0.0))
-        w = safe_float(w, 1.0)
-        if input_masks is None:
-            log.warning(
-                "IMASK requires you to attach custom masks to the CLIP object using PCAddMasksToClIP before using it"
-            )
-            input_masks = []
-
-        if len(input_masks) < idx + 1:
-            log.warning("IMASK index %s not found, ignoring...", idx)
-            continue
-        nextmask = input_masks[idx] * w
-        if i < len(feathers):
-            nextmask = feather(feathers[i].args, nextmask)
-        i += 1
-        mask = call_node(MaskComposite, mask, nextmask, 0, 0, op)[0] if mask is not None else nextmask
-
-    # apply leftover FEATHER() specs to the whole
-    for f in feathers[i:]:
-        mask = feather(f.args, mask)
-
-    return text, mask, totalweight
-
-
-def get_noise(text):
-    text, noises = get_function(
-        text,
-        "NOISE",
-        ["0.0", "none"],
-    )
-    if not noises:
-        return text, None, None
-    w = 0
-    # Only take seed from first noise spec, for simplicity
-    seed = noises[0].args[0].strip()
-    if seed == "none":
-        gen = None
-    else:
-        seed = safe_float(seed, 0)
-        gen = torch.Generator()
-        gen.manual_seed(int(seed))
-    for n in noises:
-        w += safe_float(n.args[0], 0.0)
-    return text, max(min(w, 1.0), 0.0), gen
-
-
-def apply_noise(cond, weight, gen):
-    if cond is None or not weight:
-        return cond
-
-    n = torch.randn(cond.size(), generator=gen).to(cond)
-
-    return cond * (1 - weight) + n * weight
-
-
-def process_settings(prompt, defaults, masks, mask_size, sdxl_opts):
-    if "ATTN()" in prompt:
-        raise ValueError("ATTN() no longer works and has been replaced by COUPLE()")
-
-    def weight(t):
-        opts = {}
-        m = re.search(r":(-?\d\.?\d*)(![A-Za-z]+)?$", t.strip())
-        if not m:
-            return (None, opts, t)
-        w = float(m[1])
-        tag = m[2]
-        t = t[: m.span()[0]]
-        if tag == "!noscale":
-            opts["scale"] = 1
-
-        return w, opts, t
-
-    settings = {"prompt": prompt}
-
-    if "FILL()" in prompt:
-        prompt = prompt.replace("FILL()", "")
-        settings["x-promptcontrol.fill"] = True
-    prompt, mask, mask_weight = get_mask(prompt, mask_size, masks)
-    prompt, area = get_area(prompt)
-    prompt, local_sdxl_opts = get_sdxl(prompt, defaults)
-    # Get weight last so other syntax doesn't interfere with it
-    w, opts, prompt = weight(prompt)
-    if w is not None:
-        settings["strength"] = w
-    settings.update(sdxl_opts)
-    settings.update(local_sdxl_opts)
-    if area:
-        settings["area"] = area[0]
-        settings["strength"] = area[1]
-        settings["set_area_to_bounds"] = False
-    if mask is not None:
-        settings["mask"] = mask
-        settings["mask_strength"] = mask_weight
-
-    return prompt, settings
-
-
-def encode_prompt(clip, text, start_pct, end_pct, defaults, masks):
-    # First style modifier applies to ANDed prompts too unless overridden
-    style, normalization, text = get_style(text)
-    text, mask_size = get_mask_size(text, defaults)
-
-    prompts = list(split_quotable(text, r"\bAND\b"))
-
-    p, sdxl_opts = get_sdxl(prompts[0], defaults)
-    prompts[0] = p
-
-    conds = []
-    # TODO: is this still needed?
-    # scale = sum(abs(weight(p)[0]) for p in prompts if not ("AREA(" in p or "MASK(" in p))
-
-    def ensure_mask(c):
-        if "mask" not in c[1]:
-            _, mask, _ = get_mask("MASK()", mask_size, masks)
-            c[1]["mask"] = mask
-            c[1]["mask_strength"] = 1.0
-        return c
-
-    def couple_mask(args):
-        assert len(args) <= 1, "Argument parsing failure. This is a bug in Prompt Control"
-        if not args:
-            return ""
-        return f"MASK({args[0]})"
-
-    for prompt in prompts:
-        prompt, noise_w, generator = get_noise(prompt)
-        base_prompt, attn_couple_prompts = split_by_function(prompt, "COUPLE", defaults=None, require_args=False)
-
-        prompts = [base_prompt] + [couple_mask(f.args) + chunk for (chunk, f) in attn_couple_prompts]
-        encoded = []
-        for p in prompts:
-            p, settings = process_settings(p, defaults, masks, mask_size, sdxl_opts)
-            if settings.get("strength") == 0:  # weight is explicitly set to 0, skip
-                continue
-            settings["start_percent"] = start_pct
-            settings["end_percent"] = end_pct
-            x = encode_prompt_segment(clip, p, settings, style, normalization)
-            encoded.append(x)
-
-        assert all(len(c) == len(encoded[0]) for c in encoded), (
-            "All encoded prompts didn't produce the same number of conds, I don't know what to do in this situation."
-        )
-
-        # each call to encode_prompt_segment can produce a number of conds based on any
-        # scheduled LoRA hooks on the clip model. Zip them together with coupled prompts
-        base_cond = []
-        for base_cond, *attention_couple in zip(*encoded, strict=False):
-            s = base_cond[1]
-            # If there are LoRAs on the CLIP, we need to fix start_percent and
-            # end_percent on the new conds for things to work properly.
-            s["start_percent"] = s.get("clip_start_percent", s["start_percent"])
-            s["end_percent"] = s.get("clip_end_percent", s["end_percent"])
-            s.pop("clip_start_percent", None)
-            s.pop("clip_end_percent", None)
-            base_cond = [base_cond]
-            if attention_couple:
-                fill = base_cond[0][1].get("x-promptcontrol.fill")
-                if not fill:
-                    ensure_mask(base_cond[0])
-                # else, set_cond_attnmask will have the base mask fill any unspecified areas
-                base_cond = set_cond_attnmask(
-                    base_cond,
-                    [ensure_mask(c) for c in attention_couple],
-                    fill=fill,
-                )
-
-        base_cond = [[apply_noise(c[0], noise_w, generator), c[1]] for c in base_cond]
-        conds.extend(base_cond)
-
-    return conds

prompt_control/utils.py

@@ -1,118 +1,13 @@
-from __future__ import annotations
-
-import copy
-import logging
-import re
-from collections.abc import Callable, Iterator
-from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, TypeAlias, TypeVar
+import re
+import logging
 
-if TYPE_CHECKING:
-    import torch  # flakes8: noqa
+import folder_paths
 
-FunctionArgs: TypeAlias = list[str]
-ComfyConditioning: TypeAlias = tuple["torch.Tensor", dict[str, Any]]
+log = logging.getLogger("comfyui-prompt-control-legacy")
 
 
-@dataclass
-class FunctionSpec:
-    name: str
-    args: FunctionArgs
-    position: int
-
-
-# Allow testing
-try:
-    from folder_paths import get_filename_list
-except ImportError:
-
-    def get_filename_list(folder_name) -> list[str]:
-        return []
-
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def flatten(x):
-    if type(x) in [str, tuple, int, type(None)] or isinstance(x, dict) and "type" in x:
-        yield x
-    else:
-        for g in x:
-            yield from flatten(g)
-
-
-def call_node(cls, *args, **kwargs):
-    if hasattr(cls, "execute"):
-        # v3 node
-        return cls.execute(*args, **kwargs)
-    else:
-        func = getattr(cls(), cls.FUNCTION)
-        return func(*args, **kwargs)
-
-
-def consolidate_schedule(prompt_schedule):
-    prev_loras = {}
-    not_found = []
-    consolidated = []
-    for end_pct, c in reversed(list(prompt_schedule)):
-        loras = {}
-        for k, v in c["loras"].items():
-            if k in not_found:
-                continue
-            path = lora_name_to_file(k)
-            if path is None:
-                not_found.append(k)
-                continue
-            loras[path] = v
-
-        if loras != prev_loras:
-            consolidated.append((end_pct, loras))
-        prev_loras = loras
-    for k in not_found:
-        log.warning("LoRA '%s' not found, ignoring...", k)
-    return list(reversed(consolidated))
-
-
-def find_nonscheduled_loras(consolidated_schedule):
-    consolidated_schedule = list(consolidated_schedule)
-    if not consolidated_schedule:
-        return {}
-    last_end, candidate_loras = consolidated_schedule[0]
-    to_remove = set()
-    for candidate, weights in candidate_loras.items():
-        for end, loras in consolidated_schedule[1:]:
-            last_end = end
-            if loras.get(candidate) != weights:
-                to_remove.add(candidate)
-    # No candidates if the schedule does not span full time
-    if last_end < 1.0:
-        return {}
-    return {k: v for (k, v) in candidate_loras.items() if k not in to_remove}
-
-
-def smarter_split(separator: str, string: str) -> list[str]:
-    """Does not break () when splitting"""
-    splits = []
-    prev = 0
-    idx = 0
-    stack = 0
-    escape = False
-    for idx, x in enumerate(string):
-        if x == "(" and not escape:
-            stack += 1
-        elif x == ")" and not escape:
-            stack = max(0, stack - 1)
-        elif x == separator and stack == 0:
-            splits.append(string[prev:idx])
-            prev = idx + 1
-        escape = x == "\\"
-
-    splits.append(string[prev : idx + 1])
-    return splits
-
-
-def find_closing_paren(text: str, start: int) -> int:
+def find_closing_paren(text, start):
     stack = 1
     for i, char in enumerate(text[start:]):
         if char == ")":
@@ -121,132 +16,51 @@ def find_closing_paren(text: str, start: int) -> int:
             stack += 1
         if stack == 0:
             return start + i
-    return -1
+    # Implicit closing paren after end
+    return len(text)
 
 
-def find_function_spans(
-    text: str, func: str, require_args: bool, defaults: FunctionArgs | None
-) -> Iterator[tuple[int, int, str, FunctionArgs]]:
-    e = r"\(" if require_args else r"\b"
-    rex = re.compile(rf"\b{func}{e}", re.MULTILINE)
-
-    idx = 0
+def get_function(text, func, defaults, return_func_name=False):
+    rex = re.compile(rf"\b{func}\(", re.MULTILINE)
+    instances = []
     match = rex.search(text)
     while match:
-        start, at_paren = match.span()
-        if require_args:
-            at_paren = at_paren - 1
-        funcname = text[start:at_paren]
-        after_first_paren = at_paren + 1
-        if text[at_paren:after_first_paren] == "(":
-            end = find_closing_paren(text, after_first_paren)
-            if end < 0:
-                # Unclosed paren: skip past this match so the loop terminates
-                idx += match.end()
-                text = text[match.end() :]
-                match = rex.search(text)
-                continue
-            args = parse_strings(text[after_first_paren:end], defaults)
-            end += 1
+        # Match start, content start
+        start, after_first_paren = match.span()
+        funcname = text[start : after_first_paren - 1]
+        end = find_closing_paren(text, after_first_paren)
+        args = parse_strings(text[after_first_paren:end], defaults)
+        if return_func_name:
+            instances.append((funcname, args))
         else:
-            end = at_paren
-            args = defaults or []
-        yield idx + start, idx + end, funcname, args
-        idx = idx + end
-        text = text[end:]
+            instances.append(args)
+
+        text = text[:start] + text[end + 1 :]
         match = rex.search(text)
-
-
-def get_function(
-    text: str,
-    func: str,
-    defaults: list[str] | None,
-    processor: Callable[..., str] | None = None,
-    require_args: bool = True,
-) -> tuple[str, list[FunctionSpec]]:
-    spans = [x.span() for x in re.finditer(r'".+?"', text)]
-    instances = []
-    count = 0
-    chunks = []
-    current = 0
-    skipped = 0
-    for start, end, funcname, args in find_function_spans(text, func, require_args, defaults):
-        if spans_include(spans, start, end):
-            continue
-        instances.append(FunctionSpec(funcname, args, start - skipped))
-        skipped += end - start
-        chunks.append(text[current:start])
-        if processor:
-            chunks.append(processor(*args))
-        current = end
-        count += 1
-    chunks.append(text[current:])
-    text = "".join(chunks)
     return text, instances
 
 
-def spans_include(spans: list[tuple[int, int]], s: int, e: int) -> bool:
-    return any((s > a and e < b) for a, b in spans)
-
-
-def split_quotable(text: str, regexp: str) -> Iterator[str]:
-    start_from = 0
-    spans = [x.span() for x in re.finditer(r'".+?"', text)]
-    for x in re.finditer(regexp, text):
-        s, e = x.span()
-        if not spans_include(spans, s, e):
-            yield text[start_from:s].strip()
-            start_from = e
-    yield text[start_from:].strip()
-
-
-def split_by_function(
-    text: str, func: str, defaults: list[str] | None = None, require_args: bool = True
-) -> tuple[str, list[tuple[str, FunctionSpec]]]:
-    """
-    Splits a string by function calls, returning the leftover text
-    along with a list of functions with their associated text chunk.
-    """
-    text, functions = get_function(text, func, defaults, require_args=require_args)
-    chunks = []
-    prev = 0
-    for f in functions:
-        chunks.append(text[prev : f.position])
-        prev = f.position
-    chunks.append(text[prev:])
-    r = []
-    for i, f in enumerate(functions):
-        r.append((chunks[i + 1], f))
-    return chunks[0], r
-
-
-T = TypeVar("T")
-
-
-def parse_args(strings: list[str], arg_spec: list[tuple[Any, T]], strip: bool = True) -> list[T]:
+def parse_args(strings, arg_spec, strip=True):
     args = [s[1] for s in arg_spec]
     for i, spec in list(enumerate(arg_spec))[: len(strings)]:
         try:
             if strip:
                 strings[i] = strings[i].strip()
-            f = spec[0]
-            args[i] = f(strings[i])
+            args[i] = spec[0](strings[i])
         except ValueError:
             pass
     return args
 
 
-def parse_floats(string: str, defaults: list[float], split_re: str = ",") -> list[float]:
+def parse_floats(string, defaults, split_re=","):
     spec = [(float, d) for d in defaults]
     return parse_args(re.split(split_re, string.strip()), spec)
 
 
-def parse_strings(
-    string: str, defaults: FunctionArgs | None, split_re: str = r"(?<!\\),", replace: tuple[str, str] = (r"\,", ",")
-) -> FunctionArgs:
+def parse_strings(string, defaults, split_re=r"(?<!\\),", replace=(r"\,", ",")):
     if defaults is None:
-        return [string]
-    spec = [(str, d) for d in defaults]
+        return string
+    spec = [(lambda x: x, d) for d in defaults]
     splits = re.split(split_re, string)
     if replace:
         f, t = replace
@@ -254,7 +68,7 @@ def parse_strings(
     return parse_args(splits, spec, strip=False)
 
 
-def safe_float(f: Any, default: float) -> float:
+def safe_float(f, default):
     if f is None:
         return default
     try:
@@ -263,8 +77,8 @@ def safe_float(f: Any, default: float) -> float:
         return default
 
 
-def lora_name_to_file(name: str) -> str | None:
-    filenames = get_filename_list("loras")
+def lora_name_to_file(name):
+    filenames = folder_paths.get_filename_list("loras")
     # Return exact matches as is
     if name in filenames:
         return name
@@ -274,49 +88,4 @@ def lora_name_to_file(name: str) -> str | None:
             p = Path(f).with_suffix("")
             if p.name == n or str(p) == n:
                 return f
-    # Finally, try to find unique match from parts
-    parts = name.split()
-    search = [f for f in filenames if all(p in f for p in parts)]
-    if len(search) == 1:
-        return search[0]
-    elif len(search) > 1:
-        if len(search) > 4:
-            search[4] = "..."
-        log.warning("Ignored LoRA search 's%'; matched more than one file: %s", name, ", ".join(search[:5]))
-
     return None
-
-
-def map_inputs(input_map, inputs):
-    new_inputs = {}
-    for k in inputs:
-        key = inputs[k]
-        new_inputs[k] = key
-        if isinstance(key, list):
-            key = tuple(key)
-            x = input_map.get(key, inputs[k])
-            new_inputs[k] = x
-    return new_inputs
-
-
-def expand_graph(node_mappings, graph):
-    input_map = {}
-    new_graph = copy.deepcopy(graph)
-    for k in graph:
-        data = graph[k]
-        if not isinstance(data, dict) or "class_type" not in data or data["class_type"] not in node_mappings:
-            continue
-        node = node_mappings[data["class_type"]]()
-        inputs = map_inputs(input_map, data["inputs"].copy())
-        inputs["unique_id"] = k
-        fn = getattr(node, node.FUNCTION)
-        expansion = fn(**inputs)
-        for i, v in enumerate(expansion["result"]):
-            input_map[(k, i)] = v
-        del new_graph[k]
-        new_graph.update(expansion["expand"])
-
-    for k in new_graph:
-        data = new_graph[k]
-        data["inputs"] = map_inputs(input_map, data["inputs"])
-    return new_graph

pyproject.toml

@@ -1,48 +1,16 @@
 [project]
-name = "comfyui-prompt-control"
-description = "Nodes for prompt editing and LoRA scheduling, advanced regional prompting (including attention masking) and advanced prompt encoding, all controlled through your text prompt. Feature keywords: comfyui-prompt-control, schedule, macros, attention couple, loractl, A1111"
-version = "3.0.0-beta.10"
+name = "comfyui-prompt-control-legacy"
+description = "Legacy prompt control nodes. These exist only to allow old workflows to run"
+version = "1.2.1"
 license = { file = "LICENSE" }
-
-requires-python = ">= 3.10"
+# some lark versions older than 1.1.9 apparently have a bug that breaks things, see https://github.com/asagi4/comfyui-prompt-control/issues/35
+dependencies = ["lark >= 1.1.9"]
 
 [project.urls]
-Repository = "https://github.com/asagi4/comfyui-prompt-control"
+Repository = "https://github.com/asagi4/comfyui-prompt-control-legacy"
+#  Used by Comfy Registry https://comfyregistry.org
 
 [tool.comfy]
 PublisherId = "asagi4"
-DisplayName = "ComfyUI Prompt Control"
+DisplayName = "ComfyUI Prompt Control (LEGACY VERSION)"
 Icon = ""
-
-[tool.pyright]
-extraPaths = ["../../"]
-exclude = ["prompt_control/*test*"]
-
-[tool.ty.src]
-exclude = ["tests/*.py", "prompt_control/*test*.py", "prompt_control/parsy.py"]
-
-[tool.ty.environment]
-extra-paths = ["../.."]
-
-[tool.ty.rules]
-# ComfyUI executes give this...
-invalid-method-override = "ignore"
-
-[tool.ruff]
-exclude = ["prompt_control/parsy.py"]
-line-length = 120
-
-[tool.ruff.lint]
-# Ignore line length and let the formatter handle it
-ignore = ["E501"]
-select = [
-	"E",
-	"F",
-	"UP",
-	"B",
-	"SIM",
-	"I",
-]
-
-[tool.pytest.ini_options]
-testpaths = ["tests"]

requirements.txt

@@ -0,0 +1,2 @@
+# some lark versions older than 1.1.9 apparently have a bug that breaks things, see https://github.com/asagi4/comfyui-prompt-control/issues/35
+lark >= 1.1.9

tests/conftest.py

@@ -1,5 +0,0 @@
-import logging
-
-
-def pytest_runtest_setup(item):
-    logging.getLogger("comfyui-prompt-control").setLevel(logging.CRITICAL)

tests/test_cutout.py

@@ -1,26 +0,0 @@
-import pytest
-
-from prompt_control.cutoff_parser import parse_cuts
-
-
-@pytest.fixture(scope="module", autouse=True)
-def parser():
-    return parse_cuts
-
-
-def test_parse_no_cuts(parser):
-    prompt, cutouts = parse_cuts("a b c")
-    assert prompt == "a b c"
-    assert cutouts == []
-
-
-def test_parse_cuts(parser):
-    prompt, cutouts = parse_cuts("a [CUT:b:d:0] c")
-    assert prompt == "a b c"
-    assert cutouts == [("b", "d", 0.0, None, None, None)]
-
-
-def test_parse_cuts_multiple(parser):
-    prompt, cutouts = parse_cuts("a [CUT:b:d:0] [CUT:c:e:1.0:0.5:0.9:-]")
-    assert prompt == "a b c"
-    assert cutouts == [("b", "d", 0.0, None, None, None), ("c", "e", 1.0, 0.5, 0.9, "-")]

tests/test_encode.py

@@ -1,265 +0,0 @@
-import numpy.testing as npt
-import pytest
-
-
-def run(f, *args):
-    if hasattr(f, "execute"):
-        return f.execute(*args)
-    else:
-        return getattr(f, f.FUNCTION)(*args)
-
-
-def compare_hookgroup_mask(h1, h2):
-    assert len(h1.hooks) == len(h2.hooks)
-    for a, b in zip(h1.hooks, h2.hooks, strict=True):
-        assert (a.mask == b.mask).all()
-
-
-@pytest.fixture(scope="module")
-def text_encoder_clips():
-    import os
-    from pathlib import Path
-
-    from comfy.sd import load_clip
-
-    clips = []
-    to_test = os.environ.get("TEST_TE", "clip_l").split()
-    model_dir = os.environ.get("COMFYUI_TE_DIR", ".")
-    te_root = Path(model_dir).resolve()
-
-    if "clip_l" in to_test:
-        clip_l = load_clip(
-            ckpt_paths=[str(te_root / "clip_l.safetensors")], clip_type="stable_diffusion", model_options={}
-        )
-        clips.append(("clip_l", clip_l))
-
-    if "t5" in to_test:
-        dual = load_clip(
-            [str(te_root / "clip_l.safetensors"), str(te_root / "t5xxl_fp16.safetensors")],
-            clip_type="flux",
-            model_options={},
-        )
-        clips.append(("clip_l+t5", dual))
-
-    return clips
-
-
-@pytest.fixture
-def pc_text_encode():
-    from prompt_control.nodes_base import PCTextEncode
-
-    return PCTextEncode()
-
-
-@pytest.fixture
-def node_class_objs():
-    import comfy_extras.nodes_mask
-    import nodes
-
-    # Return all used node class objects
-    return {
-        "comfy": nodes.CLIPTextEncode(),
-        "combine": nodes.ConditioningCombine(),
-        "average": nodes.ConditioningAverage(),
-        "concat": nodes.ConditioningConcat(),
-        "zeroout": nodes.ConditioningZeroOut(),
-        "strength": nodes.ConditioningSetAreaStrength(),
-        "solidmask": comfy_extras.nodes_mask.SolidMask(),
-        "setmask": nodes.ConditioningSetMask(),
-    }
-
-
-def tensors_equal(t1, t2):
-    npt.assert_equal(t1.detach().numpy(), t2.detach().numpy())
-
-
-def cond_neq(c1, c2, key=None, key_assert=None):
-    ok = False
-    try:
-        cond_equal(c1, c2, key=key, key_assert=key_assert)
-    except AssertionError:
-        ok = True
-    if not ok:
-        raise ValueError("Tensors should not be equal")
-
-
-def cond_equal(c1, c2, key=None, key_assert=None):
-    assert len(c1) == len(c2)
-    for i in range(len(c1)):
-        a, b = c1[i], c2[i]
-        if key:
-            (key_assert or assert_equal)(a[1].get(key), b[1].get(key))
-        else:
-            tensors_equal(a[0], b[0])
-
-
-def assert_equal(a, b):
-    assert a == b
-
-
-@pytest.mark.usefixtures("text_encoder_clips", "pc_text_encode", "node_class_objs")
-class TestPCTextEncode:
-    def test_basic_encode(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        comfy = node_class_objs["comfy"]
-        combine = node_class_objs["combine"]
-        average = node_class_objs["average"]
-        concat = node_class_objs["concat"]
-        zeroout = node_class_objs["zeroout"]
-
-        for _k, clip in text_encoder_clips:
-            # No exceptions
-            run(
-                pc_text_encode,
-                clip,
-                "test AND test (test:1.2) BREAK test AND TE_WEIGHT(all=0) SDXL() AND AREA(,,) test CAT test",
-            )
-
-            # Basic
-            (c1,) = run(pc_text_encode, clip, "test")
-            (c2,) = run(comfy, clip, "test")
-            c = c2  # Used in later tests
-            cond_equal(c1, c2)
-
-            # Quotes
-            (c1,) = run(pc_text_encode, clip, 'Text saying "DOG MASK AND CAT COUPLE MASK(X)"')
-            (c2,) = run(comfy, clip, 'Text saying "DOG MASK AND CAT COUPLE MASK(X)"')
-            cond_equal(c1, c2)
-
-            # Function cornercase
-            (c1,) = run(pc_text_encode, clip, "test SDXL function")
-            (c2,) = run(comfy, clip, "test SDXL function")
-            (c3,) = run(pc_text_encode, clip, "test SDXL() function")
-            cond_equal(c1, c2)
-
-            # Weights
-            (c1,) = run(pc_text_encode, clip, "(test:1.2) (test:0.6)")
-            (c2,) = run(comfy, clip, "(test:1.2) (test:0.6)")
-            cond_equal(c1, c2)
-
-            # Concat
-            (c1,) = run(pc_text_encode, clip, "test CAT test")
-            (c2,) = run(concat, c, c)
-            cond_equal(c1, c2)
-
-            # Combine
-            (c1,) = run(pc_text_encode, clip, "test AND test")
-            (c2,) = run(combine, c, c)
-            cond_equal(c1, c2)
-
-            # Zero out
-            (c1,) = run(pc_text_encode, clip, "test TE_WEIGHT(all=0)")
-            (c2,) = run(zeroout, c)
-            cond_equal(c1, c2)
-
-            # Average
-            (c1,) = run(comfy, clip, "test1")
-            (c2,) = run(comfy, clip, "test2")
-            (c3,) = run(pc_text_encode, clip, "test1 AVG() test2")
-            (c4,) = run(pc_text_encode, clip, "test1 AVG test2")
-            (avg,) = run(average, c1, c2, 0.5)
-            cond_equal(avg, c3)
-            cond_equal(avg, c4)
-
-    def test_avg(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        comfy = node_class_objs["comfy"]
-        average = node_class_objs["average"]
-        for _k, clip in text_encoder_clips:
-            (c1,) = run(comfy, clip, "test1")
-            (c2,) = run(comfy, clip, "test2")
-            (c3,) = run(comfy, clip, "test3")
-            (c4,) = run(pc_text_encode, clip, "test1 AVG() test2 AVG() test3")
-            (c5,) = run(pc_text_encode, clip, "test1 AVG test2 AVG test3")
-            (avg1,) = run(average, c1, c2, 0.5)
-            (avg,) = run(average, avg1, c3, 0.5)
-            cond_equal(avg, c4)
-            cond_equal(avg, c5)
-
-    @pytest.mark.xfail
-    def test_failure(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        comfy = node_class_objs["comfy"]
-        for _k, clip in text_encoder_clips:
-            (c1,) = run(comfy, clip, "test SDXL function")
-            (c2,) = run(pc_text_encode, clip, "test SDXL() function")
-            cond_equal(c1, c2)
-
-    def test_weight(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        comfy = node_class_objs["comfy"]
-        combine = node_class_objs["combine"]
-        strength = node_class_objs["strength"]
-
-        for _k, clip in text_encoder_clips:
-            (c,) = run(comfy, clip, "test")
-            (c2,) = run(strength, c, 0.5)
-            # Conditioning weights
-            (a,) = run(pc_text_encode, clip, "test :0.5 AND test :0.5")
-            (b,) = run(combine, c2, c2)
-            cond_equal(a, b)
-            cond_equal(a, b, "strength")
-            # Weight == 0
-            (a,) = run(pc_text_encode, clip, "test :0.5 AND test :0 AND test")
-            (b,) = run(combine, c2, c)
-            cond_equal(a, b)
-            cond_equal(a, b, "strength")
-
-    def test_attn_couple(self, text_encoder_clips, pc_text_encode):
-        for _k, clip in text_encoder_clips:
-            (c,) = run(pc_text_encode, clip, "test COUPLE prompt1 AND test2 COUPLE prompt2")
-            (c2,) = run(pc_text_encode, clip, "test COUPLE prompt1 COUPLE test2 COUPLE prompt2")
-            assert len(c) == 2
-            assert len(c2) == 1
-
-    def test_styles(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        comfy = node_class_objs["comfy"]
-        for _k, clip in text_encoder_clips:
-            (no_weights,) = run(comfy, clip, "this prompt has no weights")
-            for style in ["comfy", "A1111", "comfy++", "compel", "down_weight", "perp"]:
-                # no weights equal comfy
-                (c,) = run(pc_text_encode, clip, "this prompt has no weights")
-                cond_equal(no_weights, c)
-                # does not fail when encoding weights
-                for normalization in ["none", "mean", "length", "mean+length", "length+mean"]:
-                    run(
-                        pc_text_encode,
-                        clip,
-                        f"STYLE({style}, {normalization}) (this prompt) (has weights:0.9), (a:1.2) (b:1.2)",
-                    )
-                    # Just checking for exceptions
-
-    def test_masks(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        comfy = node_class_objs["comfy"]
-        solidmask = node_class_objs["solidmask"]
-        setmask = node_class_objs["setmask"]
-        for _k, clip in text_encoder_clips:
-            (c1,) = run(pc_text_encode, clip, "test MASK()")
-            (c2,) = run(comfy, clip, "test")
-            (c2,) = run(setmask, c2, run(solidmask, 1.0, 512, 512)[0], "default", 1.0)
-            cond_equal(c1, c2)
-            cond_equal(c1, c2, "mask", tensors_equal)
-
-    def test_cutoff_nofail(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        for _k, clip in text_encoder_clips:
-            (c1,) = run(pc_text_encode, clip, "test [CUT:a:b:0.5]")
-
-    def test_couple_mask_shortcut(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        for _k, clip in text_encoder_clips:
-            (c,) = run(pc_text_encode, clip, "test COUPLE() prompt1")
-            (c2,) = run(pc_text_encode, clip, "test COUPLE MASK() prompt1")
-            cond_equal(c, c2)
-            cond_equal(c, c2, "hooks", compare_hookgroup_mask)
-
-            (c,) = run(pc_text_encode, clip, "test COUPLE(0 0.2, 0.5) prompt1")
-            (c2,) = run(pc_text_encode, clip, "test COUPLE MASK(0 0.2, 0.5) prompt1")
-            cond_equal(c, c2)
-            cond_equal(c, c2, "hooks", compare_hookgroup_mask)
-
-    def test_noise_weight0(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        for _k, clip in text_encoder_clips:
-            (c1,) = run(pc_text_encode, clip, "test")
-            (c2,) = run(pc_text_encode, clip, "test NOISE(0, 0)")
-            cond_equal(c1, c2)
-
-    def test_noise(self, text_encoder_clips, pc_text_encode, node_class_objs):
-        for _k, clip in text_encoder_clips:
-            (c1,) = run(pc_text_encode, clip, "test")
-            (c2,) = run(pc_text_encode, clip, "test NOISE(1, 0)")
-            cond_neq(c1, c2)

tests/test_graph.py

@@ -1,686 +0,0 @@
-import logging
-
-import pytest
-from comfy_execution.graph_utils import GraphBuilder
-
-from prompt_control.nodes_lazy import (
-    PCLazyLoraLoader,
-    PCLazyLoraLoaderAdvanced,
-    PCLazyTextEncode,
-    PCLazyTextEncodeAdvanced,
-)
-
-log = logging.getLogger("comfyui-prompt-control")
-
-
-def reset_graphbuilder_state():
-    GraphBuilder.set_default_prefix("UID", 0, 0)
-
-
-def find_file(name):
-    names = {"test": "test.safetensors", "other": "some/other.safetensors"}
-    return names.get(name)
-
-
-def as_dict(out):
-    return {"result": out.result, "expand": out.expand}
-
-
-def loraloader(text, adv=False, **kwargs):
-    reset_graphbuilder_state()
-    cls = PCLazyLoraLoaderAdvanced if adv else PCLazyLoraLoader
-    model = [0, 1]
-    clip = [0, 0]
-    return as_dict(cls.execute(model=model, clip=clip, text=text, **kwargs))
-
-
-def te(text, adv=False, **kwargs):
-    cls = PCLazyTextEncode if adv else PCLazyTextEncodeAdvanced
-    reset_graphbuilder_state()
-    clip = [0, 0]
-    return as_dict(cls.execute(clip=clip, text=text, **kwargs))
-
-
-@pytest.fixture(autouse=True)
-def patch_lora_name_to_file(monkeypatch):
-    import prompt_control.utils
-
-    monkeypatch.setattr(prompt_control.utils, "lora_name_to_file", find_file)
-
-
-@pytest.fixture(autouse=True)
-def patch_torch_cuda_current_device(monkeypatch):
-    import torch.cuda
-
-    monkeypatch.setattr(torch.cuda, "current_device", lambda: "cpu")
-
-
-def test_textencode_expansion():
-    for p in ["test", "[test:0.2] test", "[test[test::0.5]]<lora:test:1>"]:
-        r1 = te(p)
-        r2 = te(p, adv=True)
-        assert r1 == r2
-
-
-def test_textencode_alternating():
-    r = te("[a|b]")
-    expected_result = {
-        "expand": {
-            "UID.0.0.1": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "a",
-                },
-            },
-            "UID.0.0.10": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.9",
-                        0,
-                    ],
-                    "end": 0.5,
-                    "start": 0.4,
-                },
-            },
-            "UID.0.0.11": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "b",
-                },
-            },
-            "UID.0.0.12": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.11",
-                        0,
-                    ],
-                    "end": 0.6,
-                    "start": 0.5,
-                },
-            },
-            "UID.0.0.13": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "a",
-                },
-            },
-            "UID.0.0.14": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.13",
-                        0,
-                    ],
-                    "end": 0.7,
-                    "start": 0.6,
-                },
-            },
-            "UID.0.0.15": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "b",
-                },
-            },
-            "UID.0.0.16": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.15",
-                        0,
-                    ],
-                    "end": 0.8,
-                    "start": 0.7,
-                },
-            },
-            "UID.0.0.17": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "a",
-                },
-            },
-            "UID.0.0.18": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.17",
-                        0,
-                    ],
-                    "end": 0.9,
-                    "start": 0.8,
-                },
-            },
-            "UID.0.0.19": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "b",
-                },
-            },
-            "UID.0.0.2": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.1",
-                        0,
-                    ],
-                    "end": 0.1,
-                    "start": 0.0,
-                },
-            },
-            "UID.0.0.20": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.19",
-                        0,
-                    ],
-                    "end": 1.0,
-                    "start": 0.9,
-                },
-            },
-            "UID.0.0.21": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.2",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.4",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.22": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.21",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.6",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.23": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.22",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.8",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.24": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.23",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.10",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.25": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.24",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.12",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.26": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.25",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.14",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.27": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.26",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.16",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.28": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.27",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.18",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.29": {
-                "class_type": "ConditioningCombine",
-                "inputs": {
-                    "conditioning_1": [
-                        "UID.0.0.28",
-                        0,
-                    ],
-                    "conditioning_2": [
-                        "UID.0.0.20",
-                        0,
-                    ],
-                },
-            },
-            "UID.0.0.3": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "b",
-                },
-            },
-            "UID.0.0.4": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.3",
-                        0,
-                    ],
-                    "end": 0.2,
-                    "start": 0.1,
-                },
-            },
-            "UID.0.0.5": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "a",
-                },
-            },
-            "UID.0.0.6": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.5",
-                        0,
-                    ],
-                    "end": 0.3,
-                    "start": 0.2,
-                },
-            },
-            "UID.0.0.7": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "b",
-                },
-            },
-            "UID.0.0.8": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {
-                    "conditioning": [
-                        "UID.0.0.7",
-                        0,
-                    ],
-                    "end": 0.4,
-                    "start": 0.3,
-                },
-            },
-            "UID.0.0.9": {
-                "class_type": "PCTextEncode",
-                "inputs": {
-                    "clip": [
-                        0,
-                        0,
-                    ],
-                    "text": "a",
-                },
-            },
-        },
-        "result": (
-            [
-                "UID.0.0.29",
-                0,
-            ],
-        ),
-    }
-    assert r == expected_result
-
-
-def test_textencode_lora():
-    reset_graphbuilder_state()
-    r = te("test<lora:test:1>")
-    assert r == {
-        "result": (["UID.0.0.2", 0],),
-        "expand": {
-            "UID.0.0.1": {"class_type": "PCTextEncode", "inputs": {"clip": [0, 0], "text": "test"}},
-            "UID.0.0.2": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.1", 0], "start": 0.0, "end": 1.0},
-            },
-        },
-    }
-
-
-def test_textencode_lora_with_schedule():
-    r = te("simple [test:0.1,0.5] prompt<lora:test:1>")
-    assert r == {
-        "result": (["UID.0.0.8", 0],),
-        "expand": {
-            "UID.0.0.1": {
-                "class_type": "PCTextEncode",
-                "inputs": {"clip": [0, 0], "text": "simple  prompt"},
-            },
-            "UID.0.0.2": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.1", 0], "start": 0.0, "end": 0.1},
-            },
-            "UID.0.0.3": {
-                "class_type": "PCTextEncode",
-                "inputs": {"clip": [0, 0], "text": "simple test prompt"},
-            },
-            "UID.0.0.4": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.3", 0], "start": 0.1, "end": 0.5},
-            },
-            "UID.0.0.5": {
-                "class_type": "PCTextEncode",
-                "inputs": {"clip": [0, 0], "text": "simple  prompt"},
-            },
-            "UID.0.0.6": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.5", 0], "start": 0.5, "end": 1.0},
-            },
-            "UID.0.0.7": {
-                "class_type": "ConditioningCombine",
-                "inputs": {"conditioning_1": ["UID.0.0.2", 0], "conditioning_2": ["UID.0.0.4", 0]},
-            },
-            "UID.0.0.8": {
-                "class_type": "ConditioningCombine",
-                "inputs": {"conditioning_1": ["UID.0.0.7", 0], "conditioning_2": ["UID.0.0.6", 0]},
-            },
-        },
-    }
-
-
-def test_textencode_custom():
-    r = te("NODE(CLIPTextEncode)simple [test:0.1,0.5] $p SEG(p) prompt")
-    assert r == {
-        "result": (["UID.0.0.8", 0],),
-        "expand": {
-            "UID.0.0.1": {
-                "class_type": "CLIPTextEncode",
-                "inputs": {"clip": [0, 0], "text": "simple  prompt"},
-            },
-            "UID.0.0.2": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.1", 0], "start": 0.0, "end": 0.1},
-            },
-            "UID.0.0.3": {
-                "class_type": "CLIPTextEncode",
-                "inputs": {"clip": [0, 0], "text": "simple test prompt"},
-            },
-            "UID.0.0.4": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.3", 0], "start": 0.1, "end": 0.5},
-            },
-            "UID.0.0.5": {
-                "class_type": "CLIPTextEncode",
-                "inputs": {"clip": [0, 0], "text": "simple  prompt"},
-            },
-            "UID.0.0.6": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.5", 0], "start": 0.5, "end": 1.0},
-            },
-            "UID.0.0.7": {
-                "class_type": "ConditioningCombine",
-                "inputs": {"conditioning_1": ["UID.0.0.2", 0], "conditioning_2": ["UID.0.0.4", 0]},
-            },
-            "UID.0.0.8": {
-                "class_type": "ConditioningCombine",
-                "inputs": {"conditioning_1": ["UID.0.0.7", 0], "conditioning_2": ["UID.0.0.6", 0]},
-            },
-        },
-    }
-
-
-def test_textencode_custom_extra():
-    r = te(
-        'NODE(CustomTextEncode, prompt, image ["1\:1", 0]; option "test"; float [10.0:__EMPTY__:0.5])simple [test:0.1,0.5] prompt'
-    )
-    assert r == {
-        "result": (["UID.0.0.8", 0],),
-        "expand": {
-            "UID.0.0.1": {
-                "class_type": "CustomTextEncode",
-                "inputs": {
-                    "clip": [0, 0],
-                    "prompt": "simple  prompt",
-                    "image": ["1:1", 0],
-                    "option": "test",
-                    "float": 10.0,
-                },
-            },
-            "UID.0.0.2": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.1", 0], "start": 0.0, "end": 0.1},
-            },
-            "UID.0.0.3": {
-                "class_type": "CustomTextEncode",
-                "inputs": {
-                    "clip": [0, 0],
-                    "prompt": "simple test prompt",
-                    "image": ["1:1", 0],
-                    "option": "test",
-                    "float": 10.0,
-                },
-            },
-            "UID.0.0.4": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.3", 0], "start": 0.1, "end": 0.5},
-            },
-            "UID.0.0.5": {
-                "class_type": "CustomTextEncode",
-                "inputs": {"clip": [0, 0], "prompt": "simple  prompt", "image": ["1:1", 0], "option": "test"},
-            },
-            "UID.0.0.6": {
-                "class_type": "ConditioningSetTimestepRange",
-                "inputs": {"conditioning": ["UID.0.0.5", 0], "start": 0.5, "end": 1.0},
-            },
-            "UID.0.0.7": {
-                "class_type": "ConditioningCombine",
-                "inputs": {"conditioning_1": ["UID.0.0.2", 0], "conditioning_2": ["UID.0.0.4", 0]},
-            },
-            "UID.0.0.8": {
-                "class_type": "ConditioningCombine",
-                "inputs": {"conditioning_1": ["UID.0.0.7", 0], "conditioning_2": ["UID.0.0.6", 0]},
-            },
-        },
-    }
-
-
-def test_loraloader_empty(monkeypatch, caplog):
-    result = loraloader("prompt here <lora:nonexistent:1.0:0.5>")["expand"]
-    result_adv = loraloader("prompt here <lora:nonexistent:1.0:0.5>", adv=True)["expand"]
-    assert result == {}
-    assert result_adv == {}
-
-
-def test_loraloader_duplicate_results():
-    result = loraloader("<lora:test:1>")["expand"]
-    result2 = loraloader("prompt here <lora:test:1.0:0.5><lora:test:0:0.5>")["expand"]
-    result3 = loraloader("prompt here <lora:test:1.0:0.5><lora:test:0:0.5>", adv=True)["expand"]
-    assert result == result2
-    assert result2 == result3
-    assert result == {
-        "UID.0.0.1": {
-            "class_type": "LoraLoader",
-            "inputs": {
-                "model": [0, 1],
-                "clip": [0, 0],
-                "strength_model": 1.0,
-                "strength_clip": 1.0,
-                "lora_name": "test.safetensors",
-            },
-        }
-    }
-
-
-def test_loraloader_multiple_loras():
-    result = loraloader("<lora:test:1><lora:other:0.5>")["expand"]
-    assert result == {
-        "UID.0.0.1": {
-            "class_type": "LoraLoader",
-            "inputs": {
-                "model": [0, 1],
-                "clip": [0, 0],
-                "strength_model": 1.0,
-                "strength_clip": 1.0,
-                "lora_name": "test.safetensors",
-            },
-        },
-        "UID.0.0.2": {
-            "class_type": "LoraLoader",
-            "inputs": {
-                "model": ["UID.0.0.1", 0],
-                "clip": ["UID.0.0.1", 1],
-                "strength_model": 0.5,
-                "strength_clip": 0.5,
-                "lora_name": "some/other.safetensors",
-            },
-        },
-    }
-
-
-def test_loraloader_strength_clip():
-    result = loraloader("prompt here <lora:test:1.0:0.5>")["expand"]
-    assert result == {
-        "UID.0.0.1": {
-            "class_type": "LoraLoader",
-            "inputs": {
-                "model": [0, 1],
-                "clip": [0, 0],
-                "strength_model": 1.0,
-                "strength_clip": 0.5,
-                "lora_name": "test.safetensors",
-            },
-        }
-    }
-
-
-def test_loraloader_scheduled_compare():
-    result = loraloader("prompt [<lora:test:0.5>:0.5]")["expand"]
-    result2 = loraloader("prompt [<lora:test:0.5>:0.5]", adv=True)["expand"]
-    assert result == result2
-    expected = {
-        "UID.0.0.1": {
-            "class_type": "CreateHookLora",
-            "inputs": {"lora_name": "test.safetensors", "strength_model": 0.5, "strength_clip": 0.5},
-        },
-        "UID.0.0.2": {
-            "class_type": "CreateHookKeyframe",
-            "inputs": {"strength_mult": 0.0, "start_percent": 0.0},
-        },
-        "UID.0.0.3": {
-            "class_type": "CreateHookKeyframe",
-            "inputs": {"start_percent": 0.5, "prev_hook_kf": ["UID.0.0.2", 0], "strength_mult": 1.0},
-        },
-        "UID.0.0.4": {
-            "class_type": "SetHookKeyframes",
-            "inputs": {"hooks": ["UID.0.0.1", 0], "hook_kf": ["UID.0.0.3", 0]},
-        },
-        "UID.0.0.5": {
-            "class_type": "SetClipHooks",
-            "inputs": {
-                "clip": [0, 0],
-                "hooks": ["UID.0.0.4", 0],
-                "apply_to_conds": True,
-                "schedule_clip": True,
-            },
-        },
-    }
-    assert result == expected
-
-
-def test_loraloader_adv_start():
-    result2 = loraloader("prompt [<lora:test:0.5>:0.5]", adv=True, start=0.6)["expand"]
-    assert result2 == {
-        "UID.0.0.1": {
-            "class_type": "LoraLoader",
-            "inputs": {
-                "model": [0, 1],
-                "clip": [0, 0],
-                "strength_model": 0.5,
-                "strength_clip": 0.5,
-                "lora_name": "test.safetensors",
-            },
-        }
-    }
-
-
-def test_loraloader_end_zero():
-    result2 = loraloader("prompt [<lora:test:0.5>:0.5]", adv=True, end=0.5)["expand"]
-    assert result2 == {}
-
-
-def test_loraloader_segs():
-    result = loraloader("prompt [<lora:test:0.5>:0.5]")["expand"]
-    result2 = loraloader("prompt [$lora:0.5]\nSEG(lora)<lora:test:0.5>\nSEG(lora2)<lora:ignored:1>")["expand"]
-    assert result == result2

tests/test_macros.py

@@ -1,77 +0,0 @@
-from textwrap import dedent
-
-import pytest
-
-from prompt_control.macros import expand_macros, expand_segs
-
-
-@pytest.mark.parametrize(
-    "text, result",
-    [
-        ("DEF(X(a;b)=$1 $2 $3 d)X(A) X(A;B;C)", "A b $3 d A B C d"),
-        (
-            "DEF(MACRO()=[empty:$1:$2])MACRO MACRO(;) MACRO(;0.5) MACRO(a;0.5)",
-            "[empty::$2] [empty::] [empty::0.5] [empty:a:0.5]",
-        ),
-        ("DEF(X=$1)DEF(Y()=$1)[X Y][X() Y()][X(1) Y(1)]", "[$1 ][ ][1 1]"),
-        (
-            "DEF(C_ANIMAL=cat)DEF(D_ANIMAL=dog)DEF(IT=It is a $1_ANIMAL $10_ANIMAL)IT(D) IT(C)",
-            "It is a dog $10_ANIMAL It is a cat $10_ANIMAL",
-        ),
-    ],
-)
-def test_basic_macro(text, result):
-    assert expand_macros(text) == result
-
-
-def test_macro_recursion():
-    with pytest.raises(ValueError) as c:
-        expand_macros("DEF(X=recurse Y) DEF(Y=recurse X) X")
-    assert "Unable to resolve DEFs" in str(c.value)
-
-
-def test_parsing_cornercase():
-    r = expand_macros("This should not get stuck DEF(")
-    assert r == "This should not get stuck DEF("
-
-
-@pytest.mark.parametrize(
-    "input, output",
-    [
-        (
-            """\
-      A red $b and
-      a blue $a
-      SEG(a)
-      cat
-      SEG(b)
-
-      dog
-      SEG(c)""",
-            "A red dog and\na blue cat",
-        ),
-        (
-            """\
-    $a and $b
-    SEG(a)
-    cat, $b
-    SEG(b)
-    dog, $c
-    SEG(c)
-    tiger
-    """,
-            "cat, dog, tiger and dog, tiger",
-        ),
-        (
-            """\
-    $a
-    SEG(a)
-    a $b
-    SEG(b)
-    b $a""",
-            "a b a b $a",
-        ),
-    ],
-)
-def test_segments(input, output):
-    assert expand_segs(dedent(input)) == output

tests/test_parser.py

@@ -1,369 +0,0 @@
-import pytest
-
-from prompt_control.parser import parse_prompt_schedules as parse
-
-
-def lora_dict(*loras):
-    return {lora: {"weight": unet, "weight_clip": te} for lora, unet, te in loras}
-
-
-def prompt(until, text, *loras):
-    return (until, {"prompt": text, "loras": lora_dict(*loras)})
-
-
-def prompts_match(a, b):
-    return list(a) == list(b)
-
-
-def assert_prompt(p, at, until, text, *loras):
-    assert prompts_match(p.at_step(at), prompt(until, text, *loras))
-
-
-params = []
-
-params.append(parse)
-
-
-@pytest.fixture(scope="module", autouse=True, params=params)
-def parse(request):
-    return request.param
-
-
-@pytest.mark.parametrize("step", [0, 0.5, 1])
-def test_no_scheduling(step, parse):
-    p = parse(r"This is a (basic:0.6) (prompt) with [no scheduling] features and \(escaped parens\)")
-    expected = prompt(1.0, r"This is a (basic:0.6) (prompt) with [no scheduling] features and \(escaped parens\)")
-    assert prompts_match(p.at_step(step), expected)
-
-
-def test_integer_steps(parse):
-    p = parse("[a:b:25]", num_steps=50)
-    assert prompts_match(p.at_step(0), prompt(0.5, "a"))
-    assert prompts_match(p.at_step(25), prompt(0.5, "a"))
-    assert prompts_match(p.at_step(0.5), prompt(0.5, "a"))
-    assert prompts_match(p.at_step(0.51), prompt(1.0, "b"))
-    assert prompts_match(p.at_step(30), prompt(1.0, "b"))
-
-
-def test_mixed_steps(parse):
-    p = parse("[a:b:25] [c:d:0.25]", num_steps=50)
-    assert prompts_match(p.at_step(0), prompt(0.25, "a c"))
-    assert prompts_match(p.at_step(25), prompt(0.5, "a d"))
-    assert prompts_match(p.at_step(0.5), prompt(0.5, "a d"))
-    assert prompts_match(p.at_step(0.51), prompt(1.0, "b d"))
-    assert prompts_match(p.at_step(30), prompt(1.0, "b d"))
-
-
-@pytest.mark.parametrize("step", [0, 0.5, 1])
-def test_quote(step, parse):
-    p = parse('This is a text with a "QUOTED DEF(X=Y)"')
-    expected = prompt(1.0, 'This is a text with a "QUOTED DEF(X=Y)"')
-    assert prompts_match(p.at_step(step), expected)
-
-
-@pytest.mark.parametrize(
-    "group",
-    [
-        ["[a:0.1]", "[:a:0.1]", "[:a::0.1,1.0]", "[:a::0.1,1.0]", "[:a::0.1]"],
-        ["[before:during:after:0.1]", "[before:during:after:0.1,1.0]", "[before:during:0.1]"],
-        ["[a:0.1,0.5]", "[[a:0.1]::0.5]", "[:a::0.1,0.5]", "[a::0.1,0.5]"],
-        ["[a:b:0.5]", "[a::b:0.5,0.5]"],
-        ["[a::0.5]", "[a:::0.5,0.5]"],
-    ],
-)
-def test_equivalences(group, parse):
-    objects = [parse(g) for g in group]
-    first = objects[0].parsed_prompt
-    for obj in objects[1:]:
-        assert obj.parsed_prompt == first
-
-
-def test_basic(parse):
-    p = parse(
-        "This is a (basic:0.6) (prompt) with (very [[simple]:(basic:0.6):0.5]:1.1) [features::0.8][ and this is ignored:1]"
-    )
-    assert_prompt(p, 0.5, 0.5, "This is a (basic:0.6) (prompt) with (very [simple]:1.1) features")
-
-
-@pytest.mark.parametrize("step", [0, 0.5, 1])
-def test_basic_cornercase(parse, step):
-    p = parse("This contains[ an ignored segment in:1] the prompt")
-    assert_prompt(p, step, 1.0, "This contains the prompt")
-
-
-def test_basic_ok(parse):
-    p = parse(
-        "This is a (basic:0.6) (prompt) with (very [[simple]:(basic:0.6):0.5]:1.1) [features::0.8][ and this is ignored:1]"
-    )
-    assert_prompt(p, 0, 0.5, "This is a (basic:0.6) (prompt) with (very [simple]:1.1) features")
-    assert_prompt(p, 0.7, 0.8, "This is a (basic:0.6) (prompt) with (very (basic:0.6):1.1) features")
-    assert_prompt(p, 1.0, 1.0, "This is a (basic:0.6) (prompt) with (very (basic:0.6):1.1) ")
-
-
-@pytest.mark.parametrize("step", [0, 0.5, 1])
-def test_lora(step, parse):
-    p = parse("This is a (lora:0.6) (prompt) with [no scheduling] features <lora:foo:0.5> <lora:bar:0.5:-1.0>")
-    expected = prompt(
-        1.0, "This is a (lora:0.6) (prompt) with [no scheduling] features  ", ("foo", 0.5, 0.5), ("bar", 0.5, -1.0)
-    )
-    assert prompts_match(p.at_step(step), expected)
-
-
-def test_scheduled_lora(parse):
-    p = parse(
-        "This is a (lora:0.6) (prompt) with [scheduling] features [<lora:foo:0.5>:<lora:bar:0.5:0.2>:0.3] <lora:bar:0.5:1.0>"
-    )
-    assert_prompt(
-        p, 0.1, 0.3, "This is a (lora:0.6) (prompt) with [scheduling] features  ", ("foo", 0.5, 0.5), ("bar", 0.5, 1.0)
-    )
-    assert_prompt(p, 0.5, 1.0, "This is a (lora:0.6) (prompt) with [scheduling] features  ", ("bar", 1.0, 1.2))
-
-
-@pytest.mark.parametrize(
-    "text",
-    [
-        "This is a sequence of [SEQ:a:0.2::0.5:c:0.8][SEQ: and x:0.8]",
-        "This is a sequence of [[a:[c:0.5]:0.2]::0.8][ and x::0.8]",
-    ],
-)
-def test_seq(parse, text):
-    p = parse(text)
-    prompts = {
-        0.2: "This is a sequence of a and x",
-        0.5: "This is a sequence of  and x",
-        0.8: "This is a sequence of c and x",
-        1.0: "This is a sequence of ",
-    }
-    for k, v in prompts.items():
-        assert_prompt(p, k, k, v)
-
-
-def test_shortcuts_scheduling(parse):
-    p = parse("A schedule [a:0.1,0.7] b")
-    p2 = parse("A schedule [[a:0.1]::0.7] b")
-    p3 = parse("A schedule [a:b:0.5,0.8]")
-    p4 = parse("A schedule [[a:0.5]:b:0.8]")
-    assert p.parsed_prompt == p2.parsed_prompt
-    assert p3.parsed_prompt == p4.parsed_prompt
-
-
-@pytest.mark.parametrize(
-    "step,until,text",
-    [
-        (0, 0.1, "test excluded test"),
-        (0.2, 0.4, "test  test"),
-        (0.45, 1.0, "test excluded2 test"),
-    ],
-)
-def test_range_1(step, until, text, parse):
-    p = parse("test [excluded::excluded2:0.1,0.4] test")
-    assert_prompt(p, step, until, text)
-
-
-@pytest.mark.parametrize(
-    "step,until,text",
-    [
-        (0, 0.1, "test  test"),
-        (0.25, 0.3, "test included test"),
-        (0.15, 0.2, "test excluded test"),
-        (0.55, 0.6, "test  test"),
-        (0.95, 1.0, "test excluded2 test"),
-    ],
-)
-def test_range_2(step, until, text, parse):
-    p = parse("test [[:included::0.2,0.8]|[excluded::excluded2:0.4,0.9]:0.1] test")
-    assert_prompt(p, step, until, text)
-
-
-def test_nested(parse):
-    p = parse(
-        "This [prompt is [SEQ:[crazy:weird:0.2] stuff:0.5:<lora:cool:1>:0.7:nesting:1.0]:completely ignored with tags:HR]"
-    )
-    prompts = {
-        0.2: (0.2, "This prompt is crazy stuff"),
-        0.3: (0.5, "This prompt is weird stuff"),
-        0.5: (0.5, "This prompt is weird stuff"),
-        0.8: (1.0, "This prompt is nesting"),
-    }
-    for k in prompts:
-        exp = [prompts[k][0], {"prompt": prompts[k][1], "loras": {}}]
-        assert prompts_match(p.at_step(k), exp)
-
-    assert_prompt(p, 0.6, 0.7, "This prompt is ", ("cool", 1.0, 1.0))
-    assert_prompt(p, 0.7, 0.7, "This prompt is ", ("cool", 1.0, 1.0))
-    p2 = p.with_filters(filters="hr, xyz")
-    assert prompts_match(p2.at_step(0), p2.at_step(1))
-
-
-def test_def(parse):
-    p = parse("DEF(X=0.5) [a:b:X] DEF(test = [c:X]) test test")
-    cases = [
-        (0.2, 0.5, "a   "),
-        (0.6, 1.0, "b  c c"),
-    ]
-    for k, until, text in cases:
-        assert_prompt(p, k, until, text)
-
-    p = parse("DEF(X=[($1):($1:$2):$2])X(test;0.7)")
-    p2 = parse("[(test):(test:0.7):0.7]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-    p = parse("DEF(X=[($1):($1:$2):$2])DEF(Y=X(test;$1))Y(0.7) Y(0.5)")
-    p2 = parse("[(test):(test:0.7):0.7] [(test):(test:0.5):0.5]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-@pytest.mark.parametrize(
-    "text, cases",
-    [
-        (r"[embedding\:a:embedding\:b:0.1,0.5]", [(0.15, 0.5, r"embedding:a"), (0.55, 1, r"embedding:b")]),
-        (
-            r"[embedding\:a:embedding\:b:embedding\:c:0.1,0.5]",
-            [(0.0, 0.1, r"embedding:a"), (0.15, 0.5, r"embedding:b"), (0.55, 1, r"embedding:c")],
-        ),
-        (r"[a\:b\\:c:0.5]", [(0.0, 0.5, "a:b\\"), (0.55, 1, r"c")]),
-        (r"[a:\#b:0.5]", [(0.0, 0.5, "a"), (0.55, 1, "#b")]),
-        (r"[a:b \(test\):0.2]", [(0, 0.2, r"a"), (0.25, 1, r"b \(test\)")]),
-    ],
-)
-def test_escapes(text, cases, parse):
-    p = parse(text)
-    for step, until, val in cases:
-        assert_prompt(p, step, until, val)
-
-
-# I think these were wrong in the old parser too
-@pytest.mark.xfail(reason="Old parser behaviour, possibly buggy")
-@pytest.mark.parametrize(
-    "text, cases",
-    [
-        (r"[a:\:a:0.5] :\[a:b:0.5]", [(0, 0.5, r"a :\[a:b:0.5]"), (0.55, 1, r":a :\[a:b:0.5]")]),
-    ],
-)
-def test_escapes_fail(text, cases, parse):
-    p = parse(text)
-    for step, until, val in cases:
-        assert_prompt(p, step, until, val)
-
-
-def test_comments(parse):
-    p = parse("this is a # comment")
-    assert_prompt(p, 0, 1.0, "this is a ")
-    p = parse("this is a [comment#:scheduled:0.6]")
-    assert_prompt(p, 0, 1.0, "this is a [comment")
-    p = parse(r"this is a [comment\#:scheduled:0.6]")
-    assert_prompt(p, 0, 0.6, "this is a comment#")
-    assert_prompt(p, 0.65, 1.0, "this is a scheduled")
-    p = parse("#this is a comment\nthis is a prompt")
-    assert_prompt(p, 0, 1.0, "\nthis is a prompt")
-
-
-def test_misc(parse):
-    p = parse("[[a:c:0.5]:0.7]")
-    p2 = parse("[:[a:c:0.5]:0.7]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-    p = parse("test [[a:[b<lora:test:0.5>:0.6]:0.5]:HR]")
-    p2 = parse("test [:[a:[:b<lora:test:0.5>:0.6]:0.5]:HR]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-def test_filters(parse):
-    p = parse("test [[a:[b<lora:test:0.5>:0.6]:0.5]:HR]")
-    p2 = parse("test [:[a:[:b<lora:test:0.5>:0.6]:0.5]:HR]")
-    assert p.parsed_prompt == p2.parsed_prompt
-    pf = p.with_filters(filters="hr")
-    assert pf.parsed_prompt == p2.with_filters(filters="hr").parsed_prompt
-    assert_prompt(pf, 0, 0.5, "test a")
-    assert_prompt(pf, 0.55, 0.6, "test ")
-    assert_prompt(pf, 0.8, 1.0, "test b", ("test", 0.5, 0.5))
-
-    p = parse("[:[<lora:test:1>:c:0.5]:0.3]")
-    assert_prompt(p, 0, 0.3, "")
-    assert_prompt(p, 0.4, 0.5, "", ("test", 1.0, 1.0))
-    assert_prompt(p, 1.0, 1.0, "c")
-
-
-def test_emb(parse):
-    p = parse("an [<emb:foo>:<emb:bar>:0.5]")
-    prompts = {
-        0.2: (0.5, "an embedding:foo"),
-        0.8: (1.0, "an embedding:bar"),
-    }
-    for k, (until, val) in prompts.items():
-        assert_prompt(p, k, until, val)
-
-
-def test_alternating_defaultstep(parse):
-    p = parse("[cat|dog|tiger]")
-    p2 = parse("[cat|dog|tiger:0.1]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-def test_alternating_basic(parse):
-    p = parse("[cat|dog|tiger]")
-    p2 = parse("[cat|dog|tiger:0.1]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-@pytest.mark.parametrize(
-    "equivalent",
-    [
-        "[cat::0.1][dog:0.1,0.2][tiger:0.2,0.3][cat:0.3,0.4][dog:0.4,0.5][tiger:0.5,0.6][cat:0.6,0.7][dog:0.7,0.8][tiger:0.8,0.9][cat:0.9,1.0]"
-    ],
-)
-def test_alternating_equivalences(parse, equivalent):
-    p = parse("[cat|dog|tiger]")
-    p2 = parse(equivalent)
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-@pytest.mark.xfail(reason="Old parser behaviour")
-def test_cornercase_failure(parse):
-    """p1 returns a prompt entry until 0 at the start"""
-    p = parse("[cat:0,0.1]")
-    p2 = parse("[cat::0.1]")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-def test_cornercase_corrected(parse):
-    p = parse("[cat:0,0.1]")
-    p2 = parse("[cat::0.1]")
-    assert p.parsed_prompt[0][0] == 0.0
-    assert p.parsed_prompt[1:] == p2.parsed_prompt
-
-
-def test_ltgt_in_schedule(parse):
-    p = parse("This should [<parse> correctly:be <Picture 1>:0.1]<lora:test:1>")
-    assert_prompt(p, 0.1, 0.1, "This should <parse> correctly", ("test", 1.0, 1.0))
-    assert_prompt(p, 0.15, 1.0, "This should be <Picture 1>", ("test", 1.0, 1.0))
-
-
-def test_floats(parse):
-    p = parse("[a:b:0.5] [c:d:e:0.2,0.7] <lora:test:-0.3>")
-    p2 = parse("[a:b:.5] [c:d:e:.2,.7] <lora:test:-.3>")
-    assert p.parsed_prompt == p2.parsed_prompt
-
-
-def test_alternating_lora(parse):
-    p4 = parse("[cat|[dog:wolf<lora:canine:1>:0.5]:0.2]")
-    for i, (text, *_loras) in enumerate(
-        [(["cat"],), (["dog"],), (["cat"],), (["wolf", ("canine", 1.0, 1.0)],), (["cat"],)]
-    ):
-        step = round((i * 0.2) + 0.2, 2)
-        assert_prompt(p4, step, step, *text)
-    assert_prompt(p4, 0.7, 0.8, "wolf", ("canine", 1.0, 1.0))
-
-
-def test_alternating_nested(parse):
-    p3 = parse("[cat|[dog|wolf]|tiger]")
-    catdogtigers = ["cat", "wolf", "tiger", "cat", "dog", "tiger", "cat", "wolf", "tiger", "cat"]
-    for i, x in enumerate(catdogtigers):
-        step = round((i * 0.1) + 0.1, 2)
-        assert_prompt(p3, step, step, x)
-
-
-def test_alternating_with_tags(parse):
-    p1 = parse("[[a|b]:HR]", filters="HR")
-    p2 = parse("[a|b]")
-    assert p1.parsed_prompt == p2.parsed_prompt

tests/test_utils.py

@@ -1,7 +0,0 @@
-from prompt_control import utils
-
-
-def test_smart_split():
-    assert utils.smarter_split(",", "foo,bar") == ["foo", "bar"]
-    assert utils.smarter_split(",", "(foo,bar),zonk") == ["(foo,bar)", "zonk"]
-    assert utils.smarter_split(",", r"\(foo,bar),zonk") == [r"\(foo", "bar)", "zonk"]

tests/test_workflow.json

@@ -1,139 +0,0 @@
-{
-  "1": {
-    "inputs": {
-      "text": "positive prompt",
-      "clip": [
-        "4",
-        1
-      ]
-    },
-    "class_type": "PCLazyTextEncode",
-    "_meta": {
-      "title": "PC: Schedule prompt"
-    }
-  },
-  "2": {
-    "inputs": {
-      "ckpt_name": "$TEST_CHECKPOINT"
-    },
-    "class_type": "CheckpointLoaderSimple",
-    "_meta": {
-      "title": "Load Checkpoint"
-    }
-  },
-  "3": {
-    "inputs": {
-      "seed": 0,
-      "steps": 8,
-      "cfg": 3,
-      "sampler_name": "euler",
-      "scheduler": "simple",
-      "denoise": 1,
-      "model": [
-        "4",
-        0
-      ],
-      "positive": [
-        "9",
-        0
-      ],
-      "negative": [
-        "9",
-        1
-      ],
-      "latent_image": [
-        "5",
-        0
-      ]
-    },
-    "class_type": "KSampler",
-    "_meta": {
-      "title": "KSampler"
-    }
-  },
-  "4": {
-    "inputs": {
-      "text": "<lora:$TEST_LORA:1>",
-      "model": [
-        "2",
-        0
-      ],
-      "clip": [
-        "2",
-        1
-      ]
-    },
-    "class_type": "PCLazyLoraLoader",
-    "_meta": {
-      "title": "PC: Schedule LoRAs"
-    }
-  },
-  "5": {
-    "inputs": {
-      "width": 1024,
-      "height": 1024,
-      "batch_size": 1
-    },
-    "class_type": "EmptyLatentImage",
-    "_meta": {
-      "title": "Empty Latent Image"
-    }
-  },
-  "6": {
-    "inputs": {
-      "samples": [
-        "3",
-        0
-      ],
-      "vae": [
-        "2",
-        2
-      ]
-    },
-    "class_type": "VAEDecode",
-    "_meta": {
-      "title": "VAE Decode"
-    }
-  },
-  "7": {
-    "inputs": {
-      "images": [
-        "6",
-        0
-      ]
-    },
-    "class_type": "PreviewImage",
-    "_meta": {
-      "title": "Preview Image"
-    }
-  },
-  "8": {
-    "inputs": {
-      "text": "worst quality,",
-      "clip": [
-        "4",
-        1
-      ]
-    },
-    "class_type": "CLIPTextEncode",
-    "_meta": {
-      "title": "CLIP Text Encode (Prompt)"
-    }
-  },
-  "9": {
-    "inputs": {
-      "positive": [
-        "1",
-        0
-      ],
-      "negative": [
-        "8",
-        0
-      ]
-    },
-    "class_type": "PCAttentionCoupleBatchNegative",
-    "_meta": {
-      "title": "PC: Attention Couple (batch negative)"
-    }
-  }
-}

tests/test_workflow.py

@@ -1,40 +0,0 @@
-import json
-import os
-import uuid
-from time import sleep
-
-import pytest
-import requests
-
-
-@pytest.fixture(scope="module", autouse=True)
-def workflow(request):
-    with open(str(request.path).replace(".py", ".json")) as f:
-        data = f.read()
-    data = data.replace("$TEST_CHECKPOINT", os.environ["PC_TEST_CHECKPOINT"])
-    data = data.replace("$TEST_LORA", os.environ["PC_TEST_LORA"])
-    return json.loads(data)
-
-
-def assert_prompt(url, p):
-    timeout = 60
-    r = requests.post(f"{url}/prompt", json={"prompt": p, "client_id": str(uuid.uuid4())}).json()
-    prompt_id = r["prompt_id"]
-    r = {"status": "pending"}
-    while r["status"] in ["pending", "in_progress"]:
-        sleep(1)
-        assert timeout > 0
-        timeout -= 1
-        r = requests.get(f"{url}/api/jobs/{prompt_id}").json()
-    assert r["status"] == "completed"
-
-
-@pytest.fixture
-def comfyui():
-    return os.environ.get("PC_TEST_COMFYUI", "http://localhost:8188")
-
-
-def test_workflow(workflow, comfyui):
-    prompt = "DEF(blue=green)a blue dog and a cat sitting [COUPLE(0 0.5, 0 1) red (cat,:1.3) COUPLE(0.5 1, 0 1) (blue:1.2) dog,:0.1]"
-    workflow["1"]["inputs"]["text"] = prompt
-    assert_prompt(comfyui, workflow)

web/docs/PCAddMaskToCLIP.md

@@ -1,3 +0,0 @@
-# PC: Attach Mask
-
-Attaches custom masks to a CLIP object so that they can be referred to in prompts using `PCTextEncode` or `PC: Schedule prompt`.

web/docs/PCAddMaskToCLIPMany.md

@@ -1 +0,0 @@
-PCAddMaskToCLIP.md

web/docs/PCAttentionCoupleBatchNegative.md

@@ -1,7 +0,0 @@
-# PC: Attention Couple (batch negative)
-
-This node applies an optimization that re-enables negative cond batching when Attention Couple is in use.
-
-It improves performance when negative prompts are not scheduled, but slightly affects outputs and is not required for Attention Couple to work.
-
-Simply add it to your workflow and pass in your positive and negative prompts. It is always safe to use, as it will not do anything when it detects that the optimization can't be applied (eg. when negative prompts contain schedules)

web/docs/PCLazyLoraLoader.md

@@ -1,7 +0,0 @@
-# PC: Schedule LoRAs
-
-This node is the core of Prompt Control. It evaluates a prompt schedule and dynamically expands into a scheduled workflow consisting of necessary calls to `LoRALoader` and `Create Hook LoRA` (for scheduled LoRAs).
-
-You can use it in place or in addition to your usual `LoRA Loader` nodes; just pass in a text prompt containing your LoRA schedule (it can be shared with `PC: Schedule Prompt`). Then connect your MODEL output as usual and the CLIP output to your `PC: Schedule Prompt` nodes.
-
-For documentation on syntax, for now see the [documentation on GitHub](https://github.com/asagi4/comfyui-prompt-control/blob/master/doc/schedules.md)

web/docs/PCLazyLoraLoaderAdvanced.md

@@ -1 +0,0 @@
-PCLazyLoraLoader.md

web/docs/PCLazyTextEncode.md

@@ -1,7 +0,0 @@
-# PC: Schedule Prompt
-
-This node is the core of Prompt Control. It evaluates a prompt schedule and dynamically expands into a scheduled workflow consisting of calls to `PCTextEncode`, `SetConditioningTimesteps` and other necessary nodes.
-
-To use it, simply replace your usual `CLIP Text Encode` nodes with `PC: Schedule Prompt` nodes. For LoRA Loading, you should use `PC: Schedule LoRAs` in place (or in addition to) of your usual LoRA Loader node.
-
-For documentation on syntax, for now see the [documentation on GitHub](https://github.com/asagi4/comfyui-prompt-control/blob/master/doc/schedules.md)

web/docs/PCLazyTextEncodeAdvanced.md

@@ -1 +0,0 @@
-PCLazyTextEncode.md

web/docs/PCLoraHooksFromText.md

@@ -1,5 +0,0 @@
-# PC: LoRA Hooks from Text (non-lazy)
-
-Creates cond hooks from a LoRA schedule, if you want to apply them manually for some reason.
-
-You should not need to use this. Use `PC: Schedule LoRAs`.

web/docs/PCMacroExpand.md

@@ -1,5 +0,0 @@
-# PC: Expand Macros
-
-Expands [prompt macros](https://github.com/asagi4/comfyui-prompt-control/blob/master/doc/macros.md)
-
-You should not need to use this directly. Use `PC: Schedule Prompt` instead.

web/docs/PCSetPCTextEncodeSettings.md

@@ -1,7 +0,0 @@
-# PC: Configure PCTextEncode
-
-Configures a CLIP object with new default values used by `PCTextEncode`. Apply it before everything else.
-
-This is needed if you want to do scheduling with steps instead of denoising percentages, but otherwise it's completely optional.
-
-Note that steps are simply syntactic sugar for percentages and may not correspond to actual steps depending on the scheduler used.

web/docs/PCTextEncode.md

@@ -1,5 +0,0 @@
-# PC: Text Encode (no scheduling)
-
-This node encodes text using some special syntax for advanced features. You should rarely need to use this node directly, and instead use `PC: Schedule Prompt` which uses this node under the hood.
-
-For documentation on syntax, see the [documentation on GitHub](https://github.com/asagi4/comfyui-prompt-control/blob/master/doc/basic.md)