Release v2.0.0-rc.1 properly

Remove misleading instruction that no longer applies
No, I do not want CUDA
2025-05-21 19:10:53 +03:00 · 2025-05-21 19:09:08 +03:00 · 2025-05-20 21:46:25 +03:00 · 2025-05-20 21:35:32 +03:00 · 2025-05-20 21:28:11 +03:00 · 2025-05-20 21:13:22 +03:00
13 changed files with 727 additions and 646 deletions
@@ -7,6 +7,9 @@ on:
    paths:
      - "pyproject.toml"

+permissions:
+  issues: write
+
 jobs:
  tests:
    uses: ./.github/workflows/tests.yml
@@ -15,6 +18,7 @@ jobs:
  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
@@ -22,5 +26,4 @@ jobs:
      - name: Publish Custom Node
        uses: Comfy-Org/publish-node-action@v1
        with:
-          ## Add your own personal access token to your Github Repository secrets and reference it here.
          personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}
@@ -1,11 +1,11 @@
 name: Run tests requiring ComfyUI
 on:
-  - workflow_call
-  - workflow_dispatch
-  - push:
-      paths:
-        - prompt_control/nodes_lazy.py
-        - prompt_control/utils.py
+  workflow_call:
+  workflow_dispatch:
+  push:
+    paths:
+      - prompt_control/nodes_lazy.py
+      - prompt_control/utils.py


 jobs:
@@ -23,5 +23,6 @@ jobs:
      - uses: actions/setup-python@v5
        with:
          python-version: '3.11'
-      - run: pip install -r requirements.txt
+      - run: pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+      - run: pip install -r requirements.txt -r ComfyUI/requirements.txt
      - run: PYTHONPATH=ComfyUI python -m prompt_control.test_graph
@@ -28,6 +28,7 @@ See [features](#features) below. Things you can control via the prompt:
 - Prompt editing and filtering without noodle soup
 - LoRA loading and scheduling via ComfyUI's hook system
 - Masking, composition and area control (regional prompting)
+- Per-encoder prompts for models with multiple text encoders, such as SDXL and Flux
 - Prompt operations like `BREAK` and `AND`
 - Weight interpretation types (comfy, A1111, etc.)
 - Prompt masking with [cutoff](#cutoff)
@@ -37,9 +38,7 @@ See the [syntax documentation](doc/syntax.md)

 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](workflows/example-lazy.json?raw=1) shows LoRA scheduling and prompt editing and compares it with the same prompt implemented with built-in ComfyUI nodes.
-
-[Here](workflows/example-2pass.json?raw=1) is a two-pass workflow illustrating more features, including custom masks and filtering.
+[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.

 The tools in this repository combine well with the macro and wildcard functionality in [comfyui-utility-nodes](https://github.com/asagi4/comfyui-utility-nodes)

@@ -136,8 +135,6 @@ a (red:1.1) cat with (brown:0.9) spots and a long tail AND STYLE(A1111) an (old:
 ```
 Will interpret the first one using the default ComfyUI behaviour, the second prompt with A1111 and the last prompt with the default again

-For things (ie. the code imports) to work, the nodes must be cloned in a directory named exactly `ComfyUI_ADV_CLIP_emb`.
-
 ## Cutoff

 NOTE: Cutoff syntax might change at some point; it's pretty clunky.
@@ -26,6 +26,14 @@ 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 equivalent to `[:cat:0.5]` meaning it switches from empty to `cat` at 0.5.

+### 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.
+
 ### 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]`
@@ -112,15 +120,23 @@ The nodes do not treat SDXL models specially, but there are some utilities that

 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)`.
+### Multiple text encoders: TE
+
+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:
- 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`.
+- 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` inside `TE` does not do anything sensible; `TE(l=foo AND bar)` will parse as two prompts `TE(foo` and `bar)`. `BREAK`, `SHIFT` and `SHUFFLE` do work, however

 ### SHUFFLE and SHIFT

@@ -155,6 +171,8 @@ The function `NOISE(weight, seed)` adds some random noise into the prompt. The s

 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`
@@ -241,4 +259,8 @@ Use `ATTN()` in combination with `MASK()` or `IMASK()` to enable attention maski

 ## 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 `g`, `l`, or `t5xxl`. For example with SDXL, try `TE_WEIGHT(g=0.25, l=0.75`). The weights are applied as a multiplier to the TE output.
+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)`
@@ -1,4 +1,6 @@
 {
+  "id": "e820c2fb-9502-45b7-a864-684757dddcdf",
+  "revision": 0,
  "last_node_id": 18,
  "last_link_id": 20,
  "nodes": [
@@ -21,26 +23,26 @@
        {
          "name": "MODEL",
          "type": "MODEL",
+          "slot_index": 0,
          "links": [
            2
-          ],
-          "slot_index": 0
+          ]
        },
        {
          "name": "CLIP",
          "type": "CLIP",
+          "slot_index": 1,
          "links": [
            3
-          ],
-          "slot_index": 1
+          ]
        },
        {
          "name": "VAE",
          "type": "VAE",
+          "slot_index": 2,
          "links": [
-            16
-          ],
-          "slot_index": 2
+            18
+          ]
        }
      ],
      "properties": {
@@ -66,7 +68,7 @@
      "flags": {
        "collapsed": true
      },
-      "order": 8,
+      "order": 7,
      "mode": 0,
      "inputs": [
        {
@@ -87,10 +89,10 @@
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
+          "slot_index": 0,
          "links": [
            12
-          ],
-          "slot_index": 0
+          ]
        }
      ],
      "title": "PC: Schedule Prompt (positive)",
@@ -109,24 +111,26 @@
      "id": 3,
      "type": "PCLazyLoraLoader",
      "pos": [
-        255,
-        -765
+        257.5,
+        -745
      ],
      "size": [
        210,
-        98
+        78
      ],
      "flags": {},
-      "order": 7,
+      "order": 6,
      "mode": 0,
      "inputs": [
        {
          "name": "model",
+          "shape": 7,
          "type": "MODEL",
          "link": 2
        },
        {
          "name": "clip",
+          "shape": 7,
          "type": "CLIP",
          "link": 3
        },
@@ -143,19 +147,19 @@
        {
          "name": "MODEL",
          "type": "MODEL",
+          "slot_index": 0,
          "links": [
            17
-          ],
-          "slot_index": 0
+          ]
        },
        {
          "name": "CLIP",
          "type": "CLIP",
+          "slot_index": 1,
          "links": [
            5,
            9
-          ],
-          "slot_index": 1
+          ]
        }
      ],
      "properties": {
@@ -181,7 +185,7 @@
        474
      ],
      "flags": {},
-      "order": 10,
+      "order": 9,
      "mode": 0,
      "inputs": [
        {
@@ -209,10 +213,10 @@
        {
          "name": "LATENT",
          "type": "LATENT",
+          "slot_index": 0,
          "links": [
            15
-          ],
-          "slot_index": 0
+          ]
        }
      ],
      "properties": {
@@ -242,13 +246,16 @@
        225
      ],
      "flags": {},
-      "order": 5,
+      "order": 1,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "STRING",
          "type": "STRING",
+          "widget": {
+            "name": "text"
+          },
          "links": [
            6,
            7
@@ -277,17 +284,20 @@
        225
      ],
      "flags": {},
-      "order": 4,
+      "order": 2,
      "mode": 0,
      "inputs": [],
      "outputs": [
        {
          "name": "STRING",
          "type": "STRING",
+          "widget": {
+            "name": "text"
+          },
+          "slot_index": 0,
          "links": [
            8
-          ],
-          "slot_index": 0
+          ]
        }
      ],
      "title": "Negative prompt",
@@ -314,7 +324,7 @@
      "flags": {
        "collapsed": true
      },
-      "order": 9,
+      "order": 8,
      "mode": 0,
      "inputs": [
        {
@@ -335,10 +345,10 @@
        {
          "name": "CONDITIONING",
          "type": "CONDITIONING",
+          "slot_index": 0,
          "links": [
            13
-          ],
-          "slot_index": 0
+          ]
        }
      ],
      "title": "PC: Schedule Prompt (negative)",
@@ -365,7 +375,7 @@
        106
      ],
      "flags": {},
-      "order": 1,
+      "order": 3,
      "mode": 0,
      "inputs": [],
      "outputs": [
@@ -402,7 +412,7 @@
        46
      ],
      "flags": {},
-      "order": 11,
+      "order": 10,
      "mode": 0,
      "inputs": [
        {
@@ -420,53 +430,18 @@
        {
          "name": "IMAGE",
          "type": "IMAGE",
+          "slot_index": 0,
          "links": [
            20
-          ],
-          "slot_index": 0
+          ]
        }
      ],
      "properties": {
        "cnr_id": "comfy-core",
        "ver": "0.3.18",
        "Node name for S&R": "VAEDecode"
-      }
-    },
-    {
-      "id": 11,
-      "type": "Reroute",
-      "pos": [
-        1155,
-        -900
-      ],
-      "size": [
-        75,
-        26
-      ],
-      "flags": {},
-      "order": 6,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "",
-          "type": "*",
-          "link": 16
-        }
-      ],
-      "outputs": [
-        {
-          "name": "",
-          "type": "VAE",
-          "links": [
-            18
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "showOutputText": false,
-        "horizontal": false
-      }
+      },
+      "widgets_values": []
    },
    {
      "id": 13,
@@ -480,7 +455,7 @@
        105
      ],
      "flags": {},
-      "order": 3,
+      "order": 4,
      "mode": 0,
      "inputs": [],
      "outputs": [],
@@ -503,7 +478,7 @@
        210
      ],
      "flags": {},
-      "order": 2,
+      "order": 5,
      "mode": 0,
      "inputs": [],
      "outputs": [],
@@ -526,7 +501,7 @@
        405
      ],
      "flags": {},
-      "order": 12,
+      "order": 11,
      "mode": 0,
      "inputs": [
        {
@@ -634,14 +609,6 @@
      0,
      "LATENT"
    ],
-    [
-      16,
-      1,
-      2,
-      11,
-      0,
-      "*"
-    ],
    [
      17,
      3,
@@ -650,14 +617,6 @@
      0,
      "MODEL"
    ],
-    [
-      18,
-      11,
-      0,
-      10,
-      1,
-      "VAE"
-    ],
    [
      20,
      10,
@@ -665,6 +624,14 @@
      18,
      0,
      "IMAGE"
+    ],
+    [
+      18,
+      1,
+      2,
+      10,
+      1,
+      "VAE"
    ]
  ],
  "groups": [],
@@ -673,10 +640,28 @@
    "ds": {
      "scale": 0.8,
      "offset": [
-        588,
-        1260
+        591.75,
+        1235
      ]
-    }
+    },
+    "linkExtensions": [
+      {
+        "id": 18,
+        "parentId": 1
+      }
+    ],
+    "reroutes": [
+      {
+        "id": 1,
+        "pos": [
+          1273.75,
+          -879.5
+        ],
+        "linkIds": [
+          18
+        ]
+      }
+    ]
  },
  "version": 0.4,
  "models": [{
@@ -1,6 +1,7 @@
 import logging
 from .parser import parse_prompt_schedules
 from comfy_execution.graph_utils import GraphBuilder, is_link
+
 from comfy_execution.graph import ExecutionBlocker

 from .utils import get_function
@@ -86,7 +87,7 @@ def create_hook_nodes_for_lora(graph, path, info, existing_node, start_pct, end_
    return hook_node, next_keyframe


-def build_lora_schedule(graph, schedule, model, clip, apply_hooks=True, return_hooks=True):
+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:
@@ -129,7 +130,7 @@ def build_lora_schedule(graph, schedule, model, clip, apply_hooks=True, return_h
            n.set_input("hooks_B", h.out(0))
            res = n
        res = res.out(0)
-        if apply_hooks:
+        if clip is not None and apply_hooks:
            n = graph.node("SetClipHooks")
            n.set_input("clip", clip)
            n.set_input("hooks", res)
@@ -137,13 +138,12 @@ def build_lora_schedule(graph, schedule, model, clip, apply_hooks=True, return_h
            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))

-    if return_hooks:
-        ret = (model, clip, res)
-    else:
-        ret = (model, clip)
+    ret = (model, clip, res)

    return {"result": ret, "expand": r}

@@ -154,16 +154,15 @@ class PCLazyLoraLoaderAdvanced:
    @classmethod
    def INPUT_TYPES(s):
        return {
-            "required": {
-                "text": ("STRING", {"multiline": True}),
+            "optional": {
                "model": ("MODEL", {"rawLink": True}),
                "clip": ("CLIP", {"rawLink": True}),
-            },
-            "optional": {
+                "text": ("STRING", {"multiline": True, "default": ""}),
                "apply_hooks": ("BOOLEAN", {"default": True}),
                "tags": ("STRING", {"default": ""}),
                "start": ("FLOAT", {"min": 0.0, "max": 1.0, "default": 0.0, "step": 0.01}),
                "end": ("FLOAT", {"min": 0.0, "max": 1.0, "default": 1.0, "step": 0.01}),
+                "num_steps": ("INT", {"min": 0, "max": 10000, "default": 0, "step": 1}),
            },
            "hidden": {"unique_id": "UNIQUE_ID"},
        }
@@ -173,15 +172,16 @@ class PCLazyLoraLoaderAdvanced:
    CATEGORY = "promptcontrol"
    FUNCTION = "apply"

-    def apply(self, model, clip, text, unique_id, apply_hooks=True, tags="", start=0.0, end=1.0):
-        schedule = parse_prompt_schedules(text, filters=tags, start=start, end=end)
+    def apply(
+        self, unique_id, model=None, clip=None, text="", apply_hooks=True, tags="", start=0.0, end=1.0, num_steps=0
+    ):
+        schedule = parse_prompt_schedules(text, filters=tags, start=start, end=end, num_steps=num_steps)
        graph = GraphBuilder(f"{unique_id}-")
-        return build_lora_schedule(graph, schedule, model, clip, apply_hooks=apply_hooks, return_hooks=True)
+        r = build_lora_schedule(graph, schedule, model, clip, apply_hooks=apply_hooks)
+        return r


-class PCLazyLoraLoader:
-    CACHE_KEY = cache_key_lora
-
+class PCLazyLoraLoader(PCLazyLoraLoaderAdvanced):
    @classmethod
    def INPUT_TYPES(s):
        return {
@@ -197,19 +197,12 @@ class PCLazyLoraLoader:
        "MODEL",
        "CLIP",
    )
-    OUTPUT_TOOLTIPS = ("Returns a model and clip with LoRAs scheduled",)
    CATEGORY = "promptcontrol"
-    FUNCTION = "apply"

-    def apply(self, unique_id, model=None, clip=None, text=""):
-        graph = GraphBuilder(f"{unique_id}-")
-        schedule = parse_prompt_schedules(text)
-        if model is None and clip is None:
-            return (
-                ExecutionBlocker("No model input provided to PCLazyLoraLoader"),
-                ExecutionBlocker("No clip input provided to PCLazyLoraLoader"),
-            )
-        return build_lora_schedule(graph, schedule, model, clip, apply_hooks=True, return_hooks=False)
+    def apply(self, *args, **kwargs):
+        r = super().apply(*args, **kwargs)
+        r["result"] = r["result"][:2]
+        return r


 def build_scheduled_prompts(graph, schedules, clip):
@@ -245,32 +238,11 @@ def build_scheduled_prompts(graph, schedules, clip):
    return {"result": (node.out(0),), "expand": g}


-def cache_key_from_inputs(cachekey, text, tags="", start=0.0, end=1.0, **kwargs):
-    schedules = parse_prompt_schedules(text, filters=tags, start=start, end=end)
+def cache_key_from_inputs(cachekey, text, tags="", start=0.0, end=1.0, num_steps=0, **kwargs):
+    schedules = parse_prompt_schedules(text, filters=tags, start=start, end=end, num_steps=num_steps)
    return [(pct, s[cachekey]) for pct, s in schedules]


-class PCLazyTextEncode:
-    CACHE_KEY = cache_key_prompt
-
-    @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {"clip": ("CLIP", {"rawLink": True}), "text": ("STRING", {"multiline": True})},
-            "hidden": {"unique_id": "UNIQUE_ID"},
-        }
-
-    RETURN_TYPES = ("CONDITIONING",)
-    OUTPUT_TOOLTIPS = ("A fully encoded and scheduled conditioning",)
-    CATEGORY = "promptcontrol"
-    FUNCTION = "apply"
-
-    def apply(self, clip, text, unique_id):
-        schedules = parse_prompt_schedules(text)
-        graph = GraphBuilder(f"{unique_id}-")
-        return build_scheduled_prompts(graph, schedules, clip)
-
-
 class PCLazyTextEncodeAdvanced:
    CACHE_KEY = cache_key_prompt

@@ -282,6 +254,7 @@ class PCLazyTextEncodeAdvanced:
                "tags": ("STRING", {"default": ""}),
                "start": ("FLOAT", {"min": 0.0, "max": 1.0, "default": 0.0, "step": 0.01}),
                "end": ("FLOAT", {"min": 0.0, "max": 1.0, "default": 1.0, "step": 0.01}),
+                "num_steps": ("INT", {"min": 0, "max": 10000, "default": 0, "step": 1}),
            },
            "hidden": {"unique_id": "UNIQUE_ID"},
        }
@@ -290,12 +263,23 @@ class PCLazyTextEncodeAdvanced:
    CATEGORY = "promptcontrol"
    FUNCTION = "apply"

-    def apply(self, clip, text, unique_id, tags="", start=0.1, end=1.0):
-        schedules = parse_prompt_schedules(text, filters=tags, start=start, end=end)
+    def apply(self, clip, text, unique_id, 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(f"{unique_id}-")
        return build_scheduled_prompts(graph, schedules, clip)


+class PCLazyTextEncode(PCLazyTextEncodeAdvanced):
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {"clip": ("CLIP", {"rawLink": True}), "text": ("STRING", {"multiline": True})},
+            "hidden": {"unique_id": "UNIQUE_ID"},
+        }
+
+    CATEGORY = "promptcontrol"
+
+
 NODE_CLASS_MAPPINGS = {
    "PCLazyTextEncode": PCLazyTextEncode,
    "PCLazyTextEncodeAdvanced": PCLazyTextEncodeAdvanced,
@@ -143,7 +143,6 @@ class PCSetPCTextEncodeSettings:
        return {
            "required": {"clip": ("CLIP",)},
            "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}),
@@ -163,7 +162,6 @@ class PCSetPCTextEncodeSettings:
    def apply(
        self,
        clip,
-        steps=0,
        mask_width=512,
        mask_height=512,
        sdxl_width=1024,
@@ -174,7 +172,6 @@ class PCSetPCTextEncodeSettings:
        sdxl_crop_h=0,
    ):
        settings = {
-            "steps": steps,
            "mask_width": mask_width,
            "mask_height": mask_height,
            "sdxl_width": sdxl_width,
@@ -103,13 +103,25 @@ def clamp(a, b, c):
    return min(max(a, b), c)


-def get_steps(tree):
-    res = [100]
+def get_steps(tree, num_steps):
+    res = [num_steps or 100]

    def tostep(s):
-        w = float(s) * 100
-        w = int(clamp(0, w, 100))
-        return w
+        steps = num_steps or 100
+        if "." in str(s) or not num_steps:
+            w = float(s)
+            value = w * steps
+        else:
+            w = int(s)
+            value = w
+
+        if w > 1 and not num_steps:
+            log.warning(
+                "You haven't configured the number of steps for Prompt Control to use, %s will be clipped to 1.0", w
+            )
+            value = steps
+
+        return int(clamp(0, value, steps))

    class CollectSteps(lark.Visitor):
        def scheduled(self, tree):
@@ -131,15 +143,14 @@ def get_steps(tree):
        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)
+                w = tostep(tree.children[i * 2 + 1])
+                tree.children[i * 2 + 1] = w
                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)
+            step_size = tostep(round(float(tree.children[-1] or 0.1), 2))
            tree.children[-1] = step_size
-            res.extend([x for x in range(step_size, 100, step_size)])
+            res.extend([x for x in range(step_size, num_steps or 100, step_size)])

    CollectSteps().visit(tree)

@@ -259,29 +270,31 @@ def at_step(step, filters, tree):


 class PromptSchedule(object):
-    def __init__(self, prompt, filters="", start=0.0, end=1.0):
+    # 0 num_steps means unconfigured
+    def __init__(self, prompt, filters="", start=0.0, end=1.0, num_steps=0):
        self.filters = filters
        self.start = start
        self.end = end
+        self.num_steps = num_steps
        self.prompt = prompt.strip()
        self.defaults = {}
        self.loaded_loras = {}

-        self.parsed_prompt = self._parse()
+        self.parsed_prompt = self._parse(num_steps)

    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):
+    def _parse(self, num_steps):
        filters = [x.strip() for x in self.filters.upper().split(",")]
        try:
            parsed = []
            tree = prompt_parser.parse(self.prompt)
-            steps = get_steps(tree)
+            steps = get_steps(tree, num_steps=num_steps)

            def f(x):
-                return round(x / 100, 2)
+                return round(x / (num_steps or 100), 2)

            for t in steps:
                p = at_step(t, filters, tree)
@@ -331,6 +344,7 @@ class PromptSchedule(object):
            filters=ifspecified(filters, self.filters),
            start=ifspecified(start, self.start),
            end=ifspecified(end, self.end),
+            num_steps=self.num_steps,
        )
        return p

@@ -138,6 +138,28 @@ def fix_word_ids(tokens):
    return tokens


+def tokenize_chunks(clip, text, need_word_ids):
+    chunks = re.split(r"\bBREAK\b", text)
+    token_chunks = []
+    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
+        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])
+
+    return tokens
+
+
 def encode_prompt_segment(
    clip,
    text,
@@ -157,37 +179,46 @@ def encode_prompt_segment(

    # 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 = []
+    text, te_prompts = get_function(text, "TE", defaults=None)
    need_word_ids = True
-    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
-        t = clip.tokenize(c, return_word_ids=need_word_ids)
-        token_chunks.append(t)
-    tokens = token_chunks[0]
+    tokens = tokenize_chunks(clip, text, need_word_ids)

-    for key in tokens:
-        for c in token_chunks[1:]:
-            tokens[key].extend(c[key])
+    per_te_prompts = {}
+    if l_prompts:
+        log.warning("Note: CLIP_L is deprecated. Use TE(l=prompt) instead")
+        per_te_prompts["l"] = l_prompts

-    # 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"]
+    for prompt in te_prompts:
+        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
+        l = per_te_prompts.get(te, [])
+        l.append(prompt)
+        per_te_prompts[te] = 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"]
+    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)[key]
+            log.info("Encoded prompt with TE '%s': %s", key, prompt)
+
+    maxlen = max(len(tokens[k]) for k in tokens)
+    empty = None
+    for k in tokens:
+        while len(tokens[k]) < maxlen:
+            if empty is None:
+                empty = clip.tokenize("", return_word_ids=need_word_ids)
+            tokens[k] += empty[k]

    tokens = fix_word_ids(tokens)

@@ -211,21 +242,28 @@ def apply_weights(output, te_name, spec):
    if te_name.startswith("clip_"):
        te_name = te_name[5:]

+    default = spec.get("all", None)
+
    if isinstance(output, tuple):
        out, pooled = output
-        if te_name in spec:
-            log.info("Weighting %s output by %s", te_name, spec[te_name])
-            out = out * spec[te_name]
        pkey = te_name + "_pooled"
-        if pkey in spec:
-            log.info("Weighting %s pooled output by %s", te_name, spec[pkey])
-            pooled = pooled * spec[pkey]
+        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 = out * w
+            pooled = pooled * pooled_w

        return out, pooled
    else:
-        if te_name in spec:
-            log.info("Weighting %s output by %s", te_name, spec[te_name])
-            output = output * spec[te_name]
+        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 = output * w
        return output


@@ -1,5 +1,8 @@
 import unittest
 import unittest.mock as mock
+import logging
+
+log = logging.getLogger("comfyui-prompt-control")


 def find_file(name):
@@ -7,10 +10,17 @@ def find_file(name):
    return names.get(name)


+def apply(cls, text, **kwargs):
+    model = [0, 1]
+    clip = [0, 0]
+    return cls().apply(unique_id="UID", model=model, clip=clip, text=text, **kwargs)
+
+
+@mock.patch("prompt_control.utils.lora_name_to_file", find_file)
+@mock.patch("torch.cuda.current_device", lambda: "cpu")
 class GraphTests(unittest.TestCase):
    maxDiff = 4096

-    @mock.patch("prompt_control.utils.lora_name_to_file", find_file)
    def test_textencode(self):
        clip = [0, 0]
        from .nodes_lazy import PCLazyTextEncode, PCLazyTextEncodeAdvanced
@@ -73,23 +83,16 @@ class GraphTests(unittest.TestCase):

        model = [0, 1]
        clip = [0, 0]
-        with self.assertLogs("comfyui-prompt-control", level="WARNING") as cm:
-            result = PCLazyLoraLoader().apply(model, clip, "prompt here <lora:nonexistent:1.0:0.5>", "UID")["expand"]
-            result_adv = PCLazyLoraLoaderAdvanced().apply(model, clip, "prompt here <lora:nonexistent:1.0:0.5>", "UID")[
-                "expand"
-            ]
+        with self.assertLogs(log, level="WARNING") as cm:
+            result = apply(PCLazyLoraLoader, "prompt here <lora:nonexistent:1.0:0.5>")["expand"]
+            result_adv = apply(PCLazyLoraLoaderAdvanced, "prompt here <lora:nonexistent:1.0:0.5>")["expand"]
        self.assertIn("LoRA 'nonexistent' not found", cm.output[0])
-        self.assertIn("LoRA 'nonexistent' not found", cm.output[1])
        self.assertEqual(result, {})
        self.assertEqual(result_adv, {})

-        result = PCLazyLoraLoader().apply(model, clip, "<lora:test:1>", "UID")["expand"]
-        result2 = PCLazyLoraLoader().apply(model, clip, "prompt here <lora:test:1.0:0.5><lora:test:0:0.5>", "UID")[
-            "expand"
-        ]
-        result3 = PCLazyLoraLoaderAdvanced().apply(
-            model, clip, "prompt here <lora:test:1.0:0.5><lora:test:0:0.5>", "UID"
-        )["expand"]
+        result = apply(PCLazyLoraLoader, "<lora:test:1>")["expand"]
+        result2 = apply(PCLazyLoraLoader, "prompt here <lora:test:1.0:0.5><lora:test:0:0.5>")["expand"]
+        result3 = apply(PCLazyLoraLoaderAdvanced, "prompt here <lora:test:1.0:0.5><lora:test:0:0.5>")["expand"]
        self.assertEqual(result, result2)
        self.assertEqual(result2, result3)
        self.assertEqual(
@@ -107,7 +110,7 @@ class GraphTests(unittest.TestCase):
                }
            },
        )
-        result = PCLazyLoraLoader().apply(model, clip, "<lora:test:1><lora:other:0.5>", "UID")["expand"]
+        result = apply(PCLazyLoraLoader, "<lora:test:1><lora:other:0.5>")["expand"]
        self.assertEqual(
            result,
            {
@@ -134,7 +137,7 @@ class GraphTests(unittest.TestCase):
            },
        )

-        result = PCLazyLoraLoader().apply(model, clip, "prompt here <lora:test:1.0:0.5>", "UID")["expand"]
+        result = apply(PCLazyLoraLoader, "prompt here <lora:test:1.0:0.5>")["expand"]
        self.assertEqual(
            result,
            {
@@ -151,8 +154,8 @@ class GraphTests(unittest.TestCase):
            },
        )

-        result = PCLazyLoraLoader().apply(model, clip, "prompt [<lora:test:0.5>:0.5]", "UID")["expand"]
-        result2 = PCLazyLoraLoaderAdvanced().apply(model, clip, "prompt [<lora:test:0.5>:0.5]", "UID")["expand"]
+        result = apply(PCLazyLoraLoader, "prompt [<lora:test:0.5>:0.5]")["expand"]
+        result2 = apply(PCLazyLoraLoaderAdvanced, "prompt [<lora:test:0.5>:0.5]")["expand"]
        self.assertEqual(result, result2)
        expected = {
            "UID-1": {
@@ -186,9 +189,7 @@ class GraphTests(unittest.TestCase):
            },
        }
        self.assertEqual(result, expected)
-        result2 = PCLazyLoraLoaderAdvanced().apply(model, clip, "prompt [<lora:test:0.5>:0.5]", "UID", start=0.6)[
-            "expand"
-        ]
+        result2 = apply(PCLazyLoraLoaderAdvanced, "prompt [<lora:test:0.5>:0.5]", start=0.6)["expand"]
        self.assertEqual(
            result2,
            {
@@ -1,14 +1,13 @@
 [project]
 name = "comfyui-prompt-control"
 description = "Nodes for convenient prompt editing, making many common operations prompt-controllable"
-version = "2.0.0-beta.9"
+version = "2.0.0-rc.1"
 license = { file = "LICENSE" }
 # 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"
-#  Used by Comfy Registry https://comfyregistry.org

 [tool.comfy]
 PublisherId = "asagi4"
Author	SHA1	Message	Date
asagi4	633b2f05e0	Release v2.0.0-rc.1 properly	2025-05-21 19:10:53 +03:00
asagi4	a15135ddc5	Remove misleading instruction that no longer applies	2025-05-21 19:09:08 +03:00
asagi4	0d7e2a4e60	No, I do not want CUDA	2025-05-20 21:46:25 +03:00
asagi4	c5495832c5	Use CPU torch	2025-05-20 21:35:32 +03:00
asagi4	63d2cb3e0c	Tests are broken again...	2025-05-20 21:28:11 +03:00
asagi4	95832e801b	Make TE_WEIGHT more convenient	2025-05-20 21:13:22 +03:00
asagi4	01bd5568d0	New function: TE Fixes #106	2025-05-20 20:47:53 +03:00
asagi4	36b3638f4e	refactor: tokenize_chunks	2025-05-20 19:45:16 +03:00
asagi4	d46000ef78	Allow TE_WEIGHT(all=1.1)	2025-05-20 19:21:01 +03:00
asagi4	aba246a33c	Add a note about compositing to clarify docs, fixes #101	2025-05-05 15:33:25 +03:00
asagi4	42ae22db83	Rename the 2pass workflow for now; it needs review	2025-04-30 16:39:48 +03:00
asagi4	cb6de285cb	Fix link in README	2025-04-03 20:51:59 +03:00
asagi4	49a073bb12	Update the comparison workflow	2025-04-03 20:45:15 +03:00
asagi4	e9afe779ae	Refresh template workflow	2025-04-03 20:09:21 +03:00
asagi4	fa3b4f7da3	Fix brain typo	2025-04-02 23:25:38 +03:00
asagi4	7a76cc8c72	v2.0.0-beta.11	2025-04-02 23:17:55 +03:00
asagi4	6b1e2a5a8a	Remove steps from PCSetPCTextEncodeSettings, it can't be used	2025-04-02 23:17:55 +03:00
asagi4	9aee531c09	Allow configuring a steps value via the Advanced nodes	2025-04-02 23:17:55 +03:00
asagi4	c08bf395a6	Test cleanup	2025-04-02 23:17:55 +03:00
asagi4	1964708997	Combine PCLazyTextEncode with PCLazyTextEncodeAdvanced	2025-04-02 23:17:55 +03:00
Robin Huang snomiao asagi4	1c4b5ce0c4	chore(publish): update GitHub Actions workflow for node publishing (#99 ) - Add permissions to allow issue writing - Update action version to v1 for publish-node-action - Add condition to run job only for 'asagi4' repository owner Co-authored-by: snomiao <snomiao+comfy-pr@gmail.com> Co-authored-by: asagi4 <130366179+asagi4@users.noreply.github.com>	2025-03-22 17:12:08 +02:00
asagi4	5eabbb419c	Re-enable tests	2025-03-10 21:40:55 +02:00
asagi4	53400a029b	v2.0.0-beta.10	2025-03-10 21:39:37 +02:00
asagi4	c39605eec4	Gah, tests broke. I hate mocking	2025-03-10 21:38:03 +02:00
asagi4	dc62e638ed	How on earth does this syntax work	2025-03-10 20:30:38 +02:00
asagi4	109cac16ef	...	2025-03-10 20:27:07 +02:00
asagi4	cf6c2b3e6a	Fix github actions	2025-03-10 20:22:36 +02:00