fixed: assign max value to all start_index widget

https://github.com/ltdrdata/ComfyUI-Inspire-Pack/issues/206

README.md

@@ -2,6 +2,7 @@
 This repository offers various extension nodes for ComfyUI. Nodes here have different characteristics compared to those in the ComfyUI Impact Pack. The Impact Pack has become too large now...
 
 ## Notice:
+* v1.9.1 To avoid confusion with the `NOISE` type in core, the type name has been changed to `NOISE_IMAGE`.
 * V0.73 The Variation Seed feature is added to Regional Prompt nodes, and it is only compatible with versions Impact Pack V5.10 and above.
 * V0.69 incompatible with the outdated **ComfyUI IPAdapter Plus**. (A version dated March 24th or later is required.)
 * V0.64 add sigma_factor to RegionalPrompt... nodes required Impact Pack V4.76 or later.
@@ -24,6 +25,7 @@ This repository offers various extension nodes for ComfyUI. Nodes here have diff
   * Save LoRA Block Weight: Save LBW_MODEL as a .lbw.safetensors file
   * Load LoRA Block Weight: Load LBW_MODEL from .lbw.safetensors file
 
+
 ### SEGS Supports nodes - This is a node that supports ApplyControlNet (SEGS) from the Impact Pack.
   * `OpenPose Preprocessor Provider (SEGS)`: OpenPose preprocessor is applied for the purpose of using OpenPose ControlNet in SEGS.
       * You need to install [ControlNet Auxiliary Preprocessors](https://github.com/Fannovel16/comfyui_controlnet_aux) to use this.
@@ -34,6 +36,7 @@ This repository offers various extension nodes for ComfyUI. Nodes here have diff
     `Color Preprocessor Provider (SEGS)`, `Inpaint Preprocessor Provider (SEGS)`, `Tile Preprocessor Provider (SEGS)`, `MeshGraphormer Depth Map Preprocessor Provider (SEGS)`  
   * `MediaPipeFaceMeshDetectorProvider`: This node provides `BBOX_DETECTOR` and `SEGM_DETECTOR` that can be used in Impact Pack's Detector using the `MediaPipe-FaceMesh Preprocessor` of ControlNet Auxiliary Preprocessors.
 
+
 ### A1111 Compatibility support - These nodes assists in replicating the creation of A1111 in ComfyUI exactly.
   * `KSampler (Inspire)`: ComfyUI uses the CPU for generating random noise, while A1111 uses the GPU. One of the three factors that significantly impact reproducing A1111's results in ComfyUI can be addressed using `KSampler (Inspire)`.
       * Other point #1 : Please make sure you haven't forgotten to include 'embedding:' in the embedding used in the prompt, like 'embedding:easynegative.'
@@ -48,6 +51,7 @@ This repository offers various extension nodes for ComfyUI. Nodes here have diff
     * `variation_seed` and `variation_strength` - Initial noise generated by the seed is transformed to the shape of `variation_seed` by `variation_strength`. If `variation_strength` is 0, it only relies on the influence of the seed, and if `variation_strength` is 1.0, it is solely influenced by `variation_seed`.
       * These parameters are used when you want to maintain the composition of an image generated by the seed but wish to introduce slight changes.
 
+
 ### Sampler nodes
   * `KSampler Progress (Inspire)` - In KSampler, the sampling process generates latent batches. By using `Video Combine` node from [ComfyUI-VideoHelperSuite](https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite), you can create a video from the progress.
   * `Scheduled CFGGuider (Inspire)` - This is a CFGGuider that adjusts the schedule from from_cfg to to_cfg using linear, log, and exp methods.
@@ -59,9 +63,17 @@ This repository offers various extension nodes for ComfyUI. Nodes here have diff
     * Specify the directories located under `ComfyUI-Inspire-Pack/prompts/`
     * One prompts file can have multiple prompts separated by `---`. 
     * e.g. `prompts/example`
-  * `Load Prompts From File (Inspire)`: It sequentially reads prompts from the specified file. The output it returns is ZIPPED_PROMPT.
+    * **NOTE**: This node provides advanced option via `Show advanced`
+      * load_cap, start_index
+
+    * `Load Prompts From File (Inspire)`: It sequentially reads prompts from the specified file. The output it returns is ZIPPED_PROMPT.
     * Specify the file located under `ComfyUI-Inspire-Pack/prompts/`
-    * e.g. `prompts/example/prompt2.txt` 
+    * e.g. `prompts/example/prompt2.txt`
+    * **NOTE**: This node provides advanced option via `Show advanced`
+      * load_cap, start_index
+
+  * `Load Single Prompt From File (Inspire)`: Loads a single prompt from a file containing multiple prompts by using an index.
+  * The prompts file directory can be specified as `inspire_prompts` in `extra_model_paths.yaml`
   * `Unzip Prompt (Inspire)`: Separate ZIPPED_PROMPT into `positive`, `negative`, and name components. 
     * `positive` and `negative` represent text prompts, while `name` represents the name of the prompt. When loaded from a file using `Load Prompts From File (Inspire)`, the name corresponds to the file name.
   * `Zip Prompt (Inspire)`: Create ZIPPED_PROMPT from positive, negative, and name_opt.
@@ -141,7 +153,11 @@ This repository offers various extension nodes for ComfyUI. Nodes here have diff
   * `Shared Checkpoint Loader (Inspire)`: When loading a checkpoint through this loader, it is automatically cached in the backend cache. Additionally, if it is already cached, it retrieves it from the cache instead of loading it anew.
     * When `key_opt` is empty, the `ckpt_name` is set as the cache key. The cache key output can be used for deletion purposes with Remove Back End.
     * This node resolves the issue of reloading checkpoints during workflow switching.
+  * `Shared Diffusion Model Loader (Inspire)`: Similar to the `Shared Checkpoint Loader (Inspire)` but used for loading Diffusion models instead of Checkpoints.
+  * `Shared Text Encoder Loader (Inspire)`: Similar to the `Shared Checkpoint Loader (Inspire)` but used for loading Text Encoder models instead of Checkpoints.
+    * This node also functions as a unified node for `CLIPLoader`, `DualCLIPLoader`, and `TripleCLIPLoader`. 
   * `Stable Cascade Checkpoint Loader (Inspire)`: This node provides a feature that allows you to load the `stage_b` and `stage_c` checkpoints of Stable Cascade at once, and it also provides a backend caching feature, optionally.
+  * `Is Cached (Inspire)`: Returns whether the cache exists.
 
 ### Conditioning - Nodes for conditionings
   * `Concat Conditionings with Multiplier (Inspire)`: Concatenating an arbitrary number of Conditionings while applying a multiplier for each Conditioning. The multiplier depends on `comfy_PoP`, so [comfy_PoP](https://github.com/picturesonpictures/comfy_PoP) must be installed.
@@ -152,8 +168,13 @@ This repository offers various extension nodes for ComfyUI. Nodes here have diff
   * `IPAdapter Model Helper (Inspire)`: This provides presets that allow for easy loading of the IPAdapter related models. However, it is essential for the model's name to be accurate.
     * You can download the appropriate model through ComfyUI-Manager.
 
-### Util - Utilities
+### List - Nodes for List processing
   * `Float Range (Inspire)`: Create a float list that increases the value by `step` from `start` to `stop`. A list as large as the maximum limit is created, and when `ensure_end` is enabled, the last value of the list becomes the stop value.
+  * `Worklist To Item List (Inspire)`: The list in ComfyUI allows for repeated execution of a sub-workflow. This groups these repetitions (a.k.a. list) into a single ITEM_LIST output. ITEM_LIST can then be used in ForeachList.
+  * `▶Foreach List (Inspire)`: A starting node for performing iterative tasks by retrieving items one by one from the ITEM_LIST.\nGenerate a new intermediate_output using item and intermediate_output as inputs, then connect it to ForeachListEnd.\nNOTE:If initial_input is omitted, the first item in item_list is used as the initial value, and the processing starts from the second item in item_list.
+  * `Foreach List◀ (Inspire)`: A end node for performing iterative tasks by retrieving items one by one from the ITEM_LIST.\nNOTE:Directly connect the outputs of ForeachListBegin to 'flow_control' and 'remained_list'.
+
+### Util - Utilities
   * `ToIPAdapterPipe (Inspire)`, `FromIPAdapterPipe (Inspire)`: These nodes assists in conveniently using the bundled ipadapter_model, clip_vision, and model required for applying IPAdapter.
   * `List Counter (Inspire)`: When each item in the list traverses through this node, it increments a counter by one, generating an integer value.
   * `RGB Hex To HSV (Inspire)`: Convert an RGB hex string like `#FFD500` to HSV:
@@ -177,3 +198,5 @@ cubiq/[ComfyUI_IPAdapter_plus](https://github.com/cubiq/ComfyUI_IPAdapter_plus)
 Davemane42/[ComfyUI_Dave_CustomNode](https://github.com/Davemane42/ComfyUI_Dave_CustomNode) - Original author of ConditioningStretch, ConditioningUpscale
 
 BlenderNeko/[ComfyUI_Noise](https://github.com/BlenderNeko/ComfyUI_Noise) - slerp code for noise variation
+
+BadCafeCode/[execution-inversion-demo-comfyui](https://github.com/BadCafeCode/execution-inversion-demo-comfyui) - reference loop implementation for ComfyUI

__init__.py

@@ -2,12 +2,12 @@
 @author: Dr.Lt.Data
 @title: Inspire Pack
 @nickname: Inspire Pack
-@description: This extension provides various nodes to support Lora Block Weight and the Impact Pack.
+@description: This extension provides various nodes to support Lora Block Weight, Regional Nodes, Backend Cache, Prompt Utils, List Utils and the Impact Pack.
 """
 
 import importlib
 
-version_code = [1, 5]
+version_code = [1, 12, 1]
 version_str = f"V{version_code[0]}.{version_code[1]}" + (f'.{version_code[2]}' if len(version_code) > 2 else '')
 print(f"### Loading: ComfyUI-Inspire-Pack ({version_str})")
 

inspire/a1111_compat.py

@@ -162,7 +162,7 @@ class KSamplerAdvanced_inspire:
                 "optional":
                     {
                         "variation_method": (["linear", "slerp"],),
-                        "noise_opt": ("NOISE",),
+                        "noise_opt": ("NOISE_IMAGE",),
                         "scheduler_func_opt": ("SCHEDULER_FUNC",),
                     }
                 }
@@ -253,7 +253,7 @@ class KSamplerAdvanced_inspire_pipe:
                      },
                 "optional":
                     {
-                        "noise_opt": ("NOISE",),
+                        "noise_opt": ("NOISE_IMAGE",),
                         "scheduler_func_opt": ("SCHEDULER_FUNC",),
                     }
                 }

inspire/backend_support.py

@@ -1,5 +1,6 @@
 import json
 import os
+from .libs import common
 
 import folder_paths
 import nodes
@@ -7,6 +8,8 @@ from server import PromptServer
 
 from .libs.utils import TaggedCache, any_typ
 
+import logging
+
 root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 settings_file = os.path.join(root_dir, 'cache_settings.json')
 try:
@@ -400,6 +403,174 @@ class CheckpointLoaderSimpleShared(nodes.CheckpointLoaderSimple):
         return (None, cache_weak_hash(key))
 
 
+class LoadDiffusionModelShared(nodes.UNETLoader):
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "model_name": (folder_paths.get_filename_list("diffusion_models"), {"tooltip": "Diffusion Model Name"}),
+                              "weight_dtype": (["default", "fp8_e4m3fn", "fp8_e4m3fn_fast", "fp8_e5m2"],),
+                              "key_opt": ("STRING", {"multiline": False, "placeholder": "If empty, use 'model_name' as the key."}),
+                              "mode": (['Auto', 'Override Cache', 'Read Only'],),
+                              }
+                }
+    RETURN_TYPES = ("MODEL", "STRING")
+    RETURN_NAMES = ("model", "cache key")
+
+    FUNCTION = "doit"
+
+    CATEGORY = "InspirePack/Backend"
+
+    def doit(self, model_name, weight_dtype, key_opt, mode='Auto'):
+        if mode == 'Read Only':
+            if key_opt.strip() == '':
+                raise Exception("[LoadDiffusionModelShared] key_opt cannot be omit if mode is 'Read Only'")
+            key = key_opt.strip()
+        elif key_opt.strip() == '':
+            key = f"{model_name}_{weight_dtype}"
+        else:
+            key = key_opt.strip()
+
+        if key not in cache or mode == 'Override Cache':
+            model = self.load_unet(model_name, weight_dtype)[0]
+            update_cache(key, "diffusion", (False, model))
+            print(f"[Inspire Pack] LoadDiffusionModelShared: diffusion model '{model_name}' is cached to '{key}'.")
+        else:
+            _, (_, model) = cache[key]
+            print(f"[Inspire Pack] LoadDiffusionModelShared: Cached diffusion model '{key}' is loaded. (Loading skip)")
+
+        return model, key
+
+    @staticmethod
+    def IS_CHANGED(model_name, weight_dtype, key_opt, mode='Auto'):
+        if mode == 'Read Only':
+            if key_opt.strip() == '':
+                raise Exception("[LoadDiffusionModelShared] key_opt cannot be omit if mode is 'Read Only'")
+            key = key_opt.strip()
+        elif key_opt.strip() == '':
+            key = f"{model_name}_{weight_dtype}"
+        else:
+            key = key_opt.strip()
+
+        if mode == 'Read Only':
+            return None, cache_weak_hash(key)
+        elif mode == 'Override Cache':
+            return model_name, key
+
+        return None, cache_weak_hash(key)
+
+
+class LoadTextEncoderShared:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "model_name1": (folder_paths.get_filename_list("text_encoders"), ),
+                              "model_name2": (["None"] + folder_paths.get_filename_list("text_encoders"), ),
+                              "model_name3": (["None"] + folder_paths.get_filename_list("text_encoders"), ),
+                              "type": (["stable_diffusion", "stable_cascade", "sd3", "stable_audio", "mochi", "ltxv", "pixart", "cosmos", "sdxl", "flux", "hunyuan_video"], ),
+                              "key_opt": ("STRING", {"multiline": False, "placeholder": "If empty, use 'model_name' as the key."}),
+                              "mode": (['Auto', 'Override Cache', 'Read Only'],),
+                              },
+                "optional": { "device": (["default", "cpu"], {"advanced": True}), }
+                }
+    RETURN_TYPES = ("CLIP", "STRING")
+    RETURN_NAMES = ("clip", "cache key")
+
+    FUNCTION = "doit"
+
+    CATEGORY = "InspirePack/Backend"
+
+    DESCRIPTION = \
+        ("[Recipes single]\n"
+         "stable_diffusion: clip-l\n"
+         "stable_cascade: clip-g\n"
+         "sd3: t5 / clip-g / clip-l\n"
+         "stable_audio: t5\n"
+         "mochi: t5\n"
+         "cosmos: old t5 xxl\n\n"
+         "[Recipes dual]\n"
+         "sdxl: clip-l, clip-g\n"
+         "sd3: clip-l, clip-g / clip-l, t5 / clip-g, t5\n"
+         "flux: clip-l, t5\n\n"
+         "[Recipes triple]\n"
+         "sd3: clip-l, clip-g, t5")
+
+    def doit(self, model_name1, model_name2, model_name3, type, key_opt, mode='Auto', device="default"):
+        if mode == 'Read Only':
+            if key_opt.strip() == '':
+                raise Exception("[LoadTextEncoderShared] key_opt cannot be omit if mode is 'Read Only'")
+            key = key_opt.strip()
+        elif key_opt.strip() == '':
+            key = model_name1
+            if model_name2 is not None:
+                key += f"_{model_name2}"
+            if model_name3 is not None:
+                key += f"_{model_name3}"
+            key += f"_{type}_{device}"
+        else:
+            key = key_opt.strip()
+
+        if key not in cache or mode == 'Override Cache':
+            if model_name2 != "None" and model_name3 != "None": # triple text encoder
+                if len({model_name1, model_name2, model_name3}) < 3:
+                    logging.error("[LoadTextEncoderShared] The same model has been selected multiple times.")
+                    raise ValueError("The same model has been selected multiple times.")
+
+                if type not in ["sd3"]:
+                    logging.error("[LoadTextEncoderShared] Currently, the triple text encoder is only supported in `sd3`.")
+                    raise ValueError("Currently, the triple text encoder is only supported in `sd3`.")
+
+                res = nodes.NODE_CLASS_MAPPINGS["TripleCLIPLoader"]().load_clip(model_name1, model_name2, model_name3)[0]
+
+            elif model_name2 != "None" or model_name3 != "None": # dual text encoder
+                second_model = model_name2 if model_name2 != "None" else model_name3
+
+                if model_name1 == second_model:
+                    logging.error("[LoadTextEncoderShared] You have selected the same model for both.")
+                    raise ValueError("[LoadTextEncoderShared] You have selected the same model for both.")
+
+                if type not in ["sdxl", "sd3", "flux", "hunyuan_video"]:
+                    logging.error("[LoadTextEncoderShared] Currently, the triple text encoder is only supported in `sdxl, sd3, flux, hunyuan_video`.")
+                    raise ValueError("Currently, the triple text encoder is only supported in `sdxl, sd3, flux, hunyuan_video`.")
+
+                res = nodes.NODE_CLASS_MAPPINGS["DualCLIPLoader"]().load_clip(model_name1, second_model, type=type, device=device)[0]
+
+            else: # single text encoder
+                if type not in ["stable_diffusion", "stable_cascade", "sd3", "stable_audio", "mochi", "ltxv", "pixart", "cosmos"]:
+                    logging.error("[LoadTextEncoderShared] Currently, the single text encoder is only supported in `stable_diffusion, stable_cascade, sd3, stable_audio, mochi, ltxv, pixart, cosmos`.")
+                    raise ValueError("Currently, the single text encoder is only supported in `stable_diffusion, stable_cascade, sd3, stable_audio, mochi, ltxv, pixart, cosmos`.")
+
+                res = nodes.NODE_CLASS_MAPPINGS["CLIPLoader"]().load_clip(model_name1, type=type, device=device)[0]
+
+            update_cache(key, "diffusion", (False, res))
+            print(f"[Inspire Pack] LoadTextEncoderShared: text encoder model set is cached to '{key}'.")
+        else:
+            _, (_, res) = cache[key]
+            print(f"[Inspire Pack] LoadTextEncoderShared: Cached text encoder model set '{key}' is loaded. (Loading skip)")
+
+        return res, key
+
+    @staticmethod
+    def IS_CHANGED(model_name1, model_name2, model_name3, type, key_opt, mode='Auto', device="default"):
+        if mode == 'Read Only':
+            if key_opt.strip() == '':
+                raise Exception("[LoadTextEncoderShared] key_opt cannot be omit if mode is 'Read Only'")
+            key = key_opt.strip()
+        elif key_opt.strip() == '':
+            key = model_name1
+            if model_name2 is not None:
+                key += f"_{model_name2}"
+            if model_name3 is not None:
+                key += f"_{model_name3}"
+            key += f"_{type}_{device}"
+        else:
+            key = key_opt.strip()
+
+        if mode == 'Read Only':
+            return None, cache_weak_hash(key)
+        elif mode == 'Override Cache':
+            return f"{model_name1}_{model_name2}_{model_name3}_{type}_{device}", key
+
+        return None, cache_weak_hash(key)
+
+
 class StableCascade_CheckpointLoader:
     @classmethod
     def INPUT_TYPES(s):
@@ -478,6 +649,74 @@ class StableCascade_CheckpointLoader:
         return b_model, b_vae, c_model, c_vae, clip_vision, clip, key_b, key_c
 
 
+class IsCached:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "key": ("STRING", {"multiline": False}),
+            },
+            "hidden": {
+                "unique_id": "UNIQUE_ID"
+            }
+        }
+
+    RETURN_TYPES = ("BOOLEAN", )
+    FUNCTION = "doit"
+
+    CATEGORY = "InspirePack/Backend"
+
+    @staticmethod
+    def IS_CHANGED(key, unique_id):
+        return common.is_changed(unique_id, key in cache)
+
+    def doit(self, key, unique_id):
+        return (key in cache,)
+
+
+# WIP: not properly working, yet
+class CacheBridge:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "value": (any_typ,),
+                "mode": ("BOOLEAN", {"default": True, "label_off": "cached", "label_on": "passthrough"}),
+            },
+            "hidden": {
+                "unique_id": "UNIQUE_ID"
+            }
+        }
+
+    RETURN_TYPES = (any_typ, )
+    RETURN_NAMES = ("value",)
+
+    FUNCTION = "doit"
+
+    CATEGORY = "InspirePack/Backend"
+
+    @staticmethod
+    def IS_CHANGED(value, mode, unique_id):
+        if not mode and unique_id in common.changed_cache:
+            return common.not_changed_value(unique_id)
+        else:
+            return common.changed_value(unique_id)
+
+    def doit(self, value, mode, unique_id):
+        if not mode:
+            # cache mode
+            if unique_id not in common.changed_cache:
+                common.changed_cache[unique_id] = value
+                common.changed_count_cache[unique_id] = 0
+
+            return (common.changed_cache[unique_id],)
+        else:
+            common.changed_cache[unique_id] = value
+            common.changed_count_cache[unique_id] = 0
+
+            return (common.changed_cache[unique_id],)
+
+
 NODE_CLASS_MAPPINGS = {
     "CacheBackendData //Inspire": CacheBackendData,
     "CacheBackendDataNumberKey //Inspire": CacheBackendDataNumberKey,
@@ -489,7 +728,11 @@ NODE_CLASS_MAPPINGS = {
     "RemoveBackendDataNumberKey //Inspire": RemoveBackendDataNumberKey,
     "ShowCachedInfo //Inspire": ShowCachedInfo,
     "CheckpointLoaderSimpleShared //Inspire": CheckpointLoaderSimpleShared,
-    "StableCascade_CheckpointLoader //Inspire": StableCascade_CheckpointLoader
+    "LoadDiffusionModelShared //Inspire": LoadDiffusionModelShared,
+    "LoadTextEncoderShared //Inspire": LoadTextEncoderShared,
+    "StableCascade_CheckpointLoader //Inspire": StableCascade_CheckpointLoader,
+    "IsCached //Inspire": IsCached,
+    # "CacheBridge //Inspire": CacheBridge,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -503,5 +746,9 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "RemoveBackendDataNumberKey //Inspire": "Remove Backend Data [NumberKey] (Inspire)",
     "ShowCachedInfo //Inspire": "Show Cached Info (Inspire)",
     "CheckpointLoaderSimpleShared //Inspire": "Shared Checkpoint Loader (Inspire)",
-    "StableCascade_CheckpointLoader //Inspire": "Stable Cascade Checkpoint Loader (Inspire)"
+    "LoadDiffusionModelShared //Inspire": "Shared Diffusion Model Loader (Inspire)",
+    "LoadTextEncoderShared //Inspire": "Shared Text Encoder Loader (Inspire)",
+    "StableCascade_CheckpointLoader //Inspire": "Stable Cascade Checkpoint Loader (Inspire)",
+    "IsCached //Inspire": "Is Cached (Inspire)",
+    # "CacheBridge //Inspire": "Cache Bridge (Inspire)"
 }

inspire/conditioning_nodes.py

@@ -8,19 +8,24 @@ from nodes import MAX_RESOLUTION
 class ConcatConditioningsWithMultiplier:
     @classmethod
     def INPUT_TYPES(s):
-        flex_inputs = {}
-
         stack = inspect.stack()
-        if stack[1].function == 'get_input_data':
+        if stack[1].function == 'get_input_info':
             # bypass validation
-            for x in range(0, 100):
-                flex_inputs[f"multiplier{x}"] = ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01})
-        else:
-            flex_inputs["multiplier1"] = ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01})
+            class AllContainer:
+                def __contains__(self, item):
+                    return True
+
+                def __getitem__(self, key):
+                    return "FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}
+
+            return {
+                "required": {"conditioning1": ("CONDITIONING",), },
+                "optional": AllContainer()
+            }
 
         return {
             "required": {"conditioning1": ("CONDITIONING",), },
-            "optional": flex_inputs
+            "optional": {"multiplier1": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}), },
         }
 
     RETURN_TYPES = ("CONDITIONING",)

inspire/image_util.py

@@ -18,7 +18,7 @@ class LoadImagesFromDirBatch:
             },
             "optional": {
                 "image_load_cap": ("INT", {"default": 0, "min": 0, "step": 1}),
-                "start_index": ("INT", {"default": 0, "min": -1, "step": 1}),
+                "start_index": ("INT", {"default": 0, "min": -1, "max": 0xffffffffffffffff, "step": 1}),
                 "load_always": ("BOOLEAN", {"default": False, "label_on": "enabled", "label_off": "disabled"}),
             }
         }
@@ -121,7 +121,7 @@ class LoadImagesFromDirList:
             },
             "optional": {
                 "image_load_cap": ("INT", {"default": 0, "min": 0, "step": 1}),
-                "start_index": ("INT", {"default": 0, "min": 0, "step": 1}),
+                "start_index": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff, "step": 1}),
                 "load_always": ("BOOLEAN", {"default": False, "label_on": "enabled", "label_off": "disabled"}),
             }
         }

inspire/inspire_server.py

@@ -6,6 +6,7 @@ from enum import Enum
 from . import prompt_support
 from aiohttp import web
 from . import backend_support
+from .libs import common
 
 
 max_seed = 2**32 - 1
@@ -271,7 +272,17 @@ def populate_wildcards(json_data):
         for k, v in prompt.items():
             if 'class_type' in v and v['class_type'] == 'WildcardEncode //Inspire':
                 inputs = v['inputs']
-                if inputs['mode'] and isinstance(inputs['populated_text'], str):
+
+                # legacy adapter
+                if isinstance(inputs['mode'], bool):
+                    if inputs['mode']:
+                        new_mode = 'populate'
+                    else:
+                        new_mode = 'fixed'
+
+                    inputs['mode'] = new_mode
+
+                if inputs['mode'] == 'populate' and isinstance(inputs['populated_text'], str):
                     if isinstance(inputs['seed'], list):
                         try:
                             input_node = prompt[inputs['seed'][0]]
@@ -292,14 +303,17 @@ def populate_wildcards(json_data):
                         input_seed = int(inputs['seed'])
 
                     inputs['populated_text'] = wildcard_process(text=inputs['wildcard_text'], seed=input_seed)
-                    inputs['mode'] = False
+                    inputs['mode'] = 'reproduce'
 
                     server.PromptServer.instance.send_sync("inspire-node-feedback", {"node_id": k, "widget_name": "populated_text", "type": "text", "data": inputs['populated_text']})
                     updated_widget_values[k] = inputs['populated_text']
 
+                if inputs['mode'] == 'reproduce':
+                    server.PromptServer.instance.send_sync("inspire-node-feedback", {"node_id": k, "widget_name": "mode", "type": "text", "value": 'populate'})
+
             elif 'class_type' in v and v['class_type'] == 'MakeBasicPipe //Inspire':
                 inputs = v['inputs']
-                if inputs['wildcard_mode'] and (isinstance(inputs['positive_populated_text'], str) or isinstance(inputs['negative_populated_text'], str)):
+                if inputs['wildcard_mode'] == 'populate' and (isinstance(inputs['positive_populated_text'], str) or isinstance(inputs['negative_populated_text'], str)):
                     if isinstance(inputs['seed'], list):
                         try:
                             input_node = prompt[inputs['seed'][0]]
@@ -327,21 +341,24 @@ def populate_wildcards(json_data):
                         inputs['negative_populated_text'] = wildcard_process(text=inputs['negative_wildcard_text'], seed=input_seed)
                         server.PromptServer.instance.send_sync("inspire-node-feedback", {"node_id": k, "widget_name": "negative_populated_text", "type": "text", "data": inputs['negative_populated_text']})
 
-                    inputs['wildcard_mode'] = False
+                    inputs['wildcard_mode'] = 'reproduce'
                     mbp_updated_widget_values[k] = inputs['positive_populated_text'], inputs['negative_populated_text']
 
+                if inputs['wildcard_mode'] == 'reproduce':
+                    server.PromptServer.instance.send_sync("inspire-node-feedback", {"node_id": k, "widget_name": "wildcard_mode", "type": "text", "value": 'populate'})
+
         if 'extra_data' in json_data and 'extra_pnginfo' in json_data['extra_data']:
             extra_pnginfo = json_data['extra_data']['extra_pnginfo']
-            if 'workflow' in extra_pnginfo and 'nodes' in extra_pnginfo['workflow']:
+            if 'workflow' in extra_pnginfo and extra_pnginfo['workflow'] is not None and 'nodes' in extra_pnginfo['workflow']:
                 for node in extra_pnginfo['workflow']['nodes']:
                     key = str(node['id'])
                     if key in updated_widget_values:
                         node['widgets_values'][3] = updated_widget_values[key]
-                        node['widgets_values'][4] = False
+                        node['widgets_values'][4] = 'reproduce'
                     if key in mbp_updated_widget_values:
                         node['widgets_values'][7] = mbp_updated_widget_values[key][0]
                         node['widgets_values'][8] = mbp_updated_widget_values[key][1]
-                        node['widgets_values'][5] = False
+                        node['widgets_values'][5] = 'reproduce'
 
 
 def force_reset_useless_params(json_data):
@@ -354,6 +371,21 @@ def force_reset_useless_params(json_data):
     return json_data
 
 
+def clear_unused_node_changed_cache(json_data):
+    prompt = json_data['prompt']
+
+    unused = []
+    for x in common.changed_cache.keys():
+        if x not in prompt:
+            unused.append(x)
+
+    for x in unused:
+        del common.changed_cache[x]
+        del common.changed_count_cache[x]
+
+    return json_data
+
+
 def onprompt(json_data):
     prompt_support.list_counter_map = {}
 
@@ -367,6 +399,7 @@ def onprompt(json_data):
     populate_wildcards(json_data)
 
     force_reset_useless_params(json_data)
+    clear_unused_node_changed_cache(json_data)
 
     return json_data
 

inspire/libs/common.py

@@ -12,3 +12,30 @@ def impact_sampling(*args, **kwargs):
         raise Exception(f"[ERROR] You need to install 'ComfyUI-Impact-Pack'")
 
     return nodes.NODE_CLASS_MAPPINGS['RegionalSampler'].separated_sample(*args, **kwargs)
+
+
+changed_count_cache = {}
+changed_cache = {}
+
+
+def changed_value(uid):
+    v = changed_count_cache.get(uid, 0)
+    changed_count_cache[uid] = v + 1
+    return v + 1
+
+
+def not_changed_value(uid):
+    return changed_count_cache.get(uid, 0)
+
+
+def is_changed(uid, value):
+    if uid not in changed_cache or changed_cache[uid] != value:
+        res = changed_value(uid)
+    else:
+        res = not_changed_value(uid)
+
+    changed_cache[uid] = value
+
+    print(f"keys: {changed_cache.keys()}")
+
+    return res

inspire/list_nodes.py

@@ -1,3 +1,6 @@
+from comfy_execution.graph_utils import GraphBuilder, is_link
+from .libs.utils import any_typ
+
 class FloatRange:
     @classmethod
     def INPUT_TYPES(s):
@@ -15,7 +18,7 @@ class FloatRange:
 
     FUNCTION = "doit"
 
-    CATEGORY = "InspirePack/Util"
+    CATEGORY = "InspirePack/List"
 
     def doit(self, start, stop, step, limit, ensure_end):
         if start == stop or step == 0:
@@ -47,10 +50,170 @@ class FloatRange:
         return (res, )
 
 
+class WorklistToItemList:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                        "item": (any_typ, ),
+                     }
+                }
+
+    INPUT_IS_LIST = True
+
+    RETURN_TYPES = ("ITEM_LIST",)
+    RETURN_NAMES = ("item_list",)
+
+    FUNCTION = "doit"
+
+    DESCRIPTION = "The list in ComfyUI allows for repeated execution of a sub-workflow.\nThis groups these repetitions (a.k.a. list) into a single ITEM_LIST output.\nITEM_LIST can then be used in ForeachList."
+
+    CATEGORY = "InspirePack/List"
+
+    def doit(self, item):
+        return (item, )
+
+
+# Loop nodes are implemented based on BadCafeCode's reference loop implementation
+# https://github.com/BadCafeCode/execution-inversion-demo-comfyui/blob/main/flow_control.py
+
+class ForeachListBegin:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                        "item_list": ("ITEM_LIST", {"tooltip": "ITEM_LIST containing items to be processed iteratively."}),
+                     },
+                "optional": {
+                        "initial_input": (any_typ, {"tooltip": "If initial_input is omitted, the first item in item_list is used as the initial value, and the processing starts from the second item in item_list."}),
+                    }
+                }
+
+    RETURN_TYPES = ("FOREACH_LIST_CONTROL", "ITEM_LIST", any_typ, any_typ)
+    RETURN_NAMES = ("flow_control", "remained_list", "item", "intermediate_output")
+    OUTPUT_TOOLTIPS = (
+        "Pass ForeachListEnd as is to indicate the end of the iteration.",
+        "Output the ITEM_LIST containing the remaining items during the iteration, passing ForeachListEnd as is to indicate the end of the iteration.",
+        "Output the current item during the iteration.",
+        "Output the intermediate results during the iteration.")
+
+    FUNCTION = "doit"
+
+    DESCRIPTION = "A starting node for performing iterative tasks by retrieving items one by one from the ITEM_LIST.\nGenerate a new intermediate_output using item and intermediate_output as inputs, then connect it to ForeachListEnd.\nNOTE:If initial_input is omitted, the first item in item_list is used as the initial value, and the processing starts from the second item in item_list."
+
+    CATEGORY = "InspirePack/List"
+
+    def doit(self, item_list, initial_input=None):
+        if initial_input is None:
+            initial_input = item_list[0]
+            item_list = item_list[1:]
+            
+        if len(item_list) > 0:
+            return ("stub", item_list[1:], item_list[0], initial_input)
+
+        return ("stub", [], None, initial_input)
+
+
+class ForeachListEnd:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                        "flow_control": ("FOREACH_LIST_CONTROL", {"rawLink": True, "tooltip": "Directly connect the output of ForeachListBegin, the starting node of the iteration."}),
+                        "remained_list": ("ITEM_LIST", {"tooltip":"Directly connect the output of ForeachListBegin, the starting node of the iteration."}),
+                        "intermediate_output": (any_typ, {"tooltip":"Connect the intermediate outputs processed within the iteration here."}),
+                     },
+                "hidden": {
+                    "dynprompt": "DYNPROMPT",
+                    "unique_id": "UNIQUE_ID",
+                    }
+                }
+
+    RETURN_TYPES = (any_typ,)
+    RETURN_NAMES = ("result",)
+    OUTPUT_TOOLTIPS = ("This is the final output value.",)
+
+    FUNCTION = "doit"
+
+    DESCRIPTION = "A end node for performing iterative tasks by retrieving items one by one from the ITEM_LIST.\nNOTE:Directly connect the outputs of ForeachListBegin to 'flow_control' and 'remained_list'."
+
+    CATEGORY = "InspirePack/List"
+
+    def explore_dependencies(self, node_id, dynprompt, upstream):
+        node_info = dynprompt.get_node(node_id)
+        if "inputs" not in node_info:
+            return
+        for k, v in node_info["inputs"].items():
+            if is_link(v):
+                parent_id = v[0]
+                if parent_id not in upstream:
+                    upstream[parent_id] = []
+                    self.explore_dependencies(parent_id, dynprompt, upstream)
+                upstream[parent_id].append(node_id)
+
+    def collect_contained(self, node_id, upstream, contained):
+        if node_id not in upstream:
+            return
+        for child_id in upstream[node_id]:
+            if child_id not in contained:
+                contained[child_id] = True
+                self.collect_contained(child_id, upstream, contained)
+
+    def doit(self, flow_control, remained_list, intermediate_output, dynprompt, unique_id):
+        if len(remained_list) == 0:
+            return (intermediate_output,)
+
+        # We want to loop
+        this_node = dynprompt.get_node(unique_id)
+        upstream = {}
+
+        # Get the list of all nodes between the open and close nodes
+        self.explore_dependencies(unique_id, dynprompt, upstream)
+
+        contained = {}
+        open_node = flow_control[0]
+        self.collect_contained(open_node, upstream, contained)
+        contained[unique_id] = True
+        contained[open_node] = True
+
+        # We'll use the default prefix, but to avoid having node names grow exponentially in size,
+        # we'll use "Recurse" for the name of the recursively-generated copy of this node.
+        graph = GraphBuilder()
+        for node_id in contained:
+            original_node = dynprompt.get_node(node_id)
+            node = graph.node(original_node["class_type"], "Recurse" if node_id == unique_id else node_id)
+            node.set_override_display_id(node_id)
+
+        for node_id in contained:
+            original_node = dynprompt.get_node(node_id)
+            node = graph.lookup_node("Recurse" if node_id == unique_id else node_id)
+            for k, v in original_node["inputs"].items():
+                if is_link(v) and v[0] in contained:
+                    parent = graph.lookup_node(v[0])
+                    node.set_input(k, parent.out(v[1]))
+                else:
+                    node.set_input(k, v)
+
+        new_open = graph.lookup_node(open_node)
+        new_open.set_input("item_list", remained_list)
+        new_open.set_input("initial_input", intermediate_output)
+
+        my_clone = graph.lookup_node("Recurse" )
+        result = (my_clone.out(0),)
+
+        return {
+            "result": result,
+            "expand": graph.finalize(),
+        }
+
+
 NODE_CLASS_MAPPINGS = {
     "FloatRange //Inspire": FloatRange,
+    "WorklistToItemList //Inspire": WorklistToItemList,
+    "ForeachListBegin //Inspire": ForeachListBegin,
+    "ForeachListEnd //Inspire": ForeachListEnd,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
-    "FloatRange //Inspire": "Float Range (Inspire)"
+    "FloatRange //Inspire": "Float Range (Inspire)",
+    "WorklistToItemList //Inspire": "Worklist To Item List (Inspire)",
+    "ForeachListBegin //Inspire": "▶Foreach List (Inspire)",
+    "ForeachListEnd //Inspire": "Foreach List◀ (Inspire)",
 }

inspire/lora_block_weight.py

@@ -484,7 +484,7 @@ class LoraLoaderBlockWeight:
 
             if k in muted_weights:
                 pass
-            elif 'text' in k:
+            elif 'text' in k or 'encoder' in k:
                 new_clip.add_patches({k: weights}, strength_clip * ratio)
             else:
                 new_modelpatcher.add_patches({k: weights}, strength_model * ratio)
@@ -546,7 +546,7 @@ class ApplyLBW:
 
             if k in muted_weights:
                 pass
-            elif 'text' in k:
+            elif 'text' in k or 'encoder' in k:
                 new_clip.add_patches({k: weights}, strength_clip * ratio)
             else:
                 new_modelpatcher.add_patches({k: weights}, strength_model * ratio)
@@ -822,9 +822,13 @@ class LoraBlockInfo:
         output_blocks = []
         output_blocks_map = {}
 
-        text_block_count = set()
-        text_blocks = []
-        text_blocks_map = {}
+        text_block_count1 = set()
+        text_blocks1 = []
+        text_blocks_map1 = {}
+
+        text_block_count2 = set()
+        text_blocks2 = []
+        text_blocks_map2 = {}
 
         double_block_count = set()
         double_blocks = []
@@ -902,12 +906,23 @@ class LoraBlockInfo:
                 k_unet_num = k_unet[len("er.text_model.encoder.layers."):len("er.text_model.encoder.layers.")+2]
                 k_unet_int = parse_unet_num(k_unet_num)
 
-                text_block_count.add(k_unet_int)
-                text_blocks.append(k_unet)
-                if k_unet_int in text_blocks_map:
-                    text_blocks_map[k_unet_int].append(k_unet)
+                text_block_count1.add(k_unet_int)
+                text_blocks1.append(k_unet)
+                if k_unet_int in text_blocks_map1:
+                    text_blocks_map1[k_unet_int].append(k_unet)
                 else:
-                    text_blocks_map[k_unet_int] = [k_unet]
+                    text_blocks_map1[k_unet_int] = [k_unet]
+
+            elif k_unet.startswith("r.encoder.block."):
+                k_unet_num = k_unet[len("r.encoder.block."):len("r.encoder.block.")+2]
+                k_unet_int = parse_unet_num(k_unet_num)
+
+                text_block_count2.add(k_unet_int)
+                text_blocks2.append(k_unet)
+                if k_unet_int in text_blocks_map2:
+                    text_blocks_map2[k_unet_int].append(k_unet)
+                else:
+                    text_blocks_map2[k_unet_int] = [k_unet]
 
             else:
                 others.append(k_unet)
@@ -951,10 +966,14 @@ class LoraBlockInfo:
             for x in single_keys:
                 text += f" SINGLE{x}: {len(single_blocks_map[x])}\n"
 
-        text += f"\n-------[Base blocks] ({len(text_block_count) + len(others)}, Subs={len(text_blocks) + len(others)})-------\n"
-        text_keys = sorted(text_blocks_map.keys())
-        for x in text_keys:
-            text += f" TXT_ENC{x}: {len(text_blocks_map[x])}\n"
+        text += f"\n-------[Base blocks] ({len(text_block_count1) + len(text_block_count2) + len(others)}, Subs={len(text_blocks1) + len(text_blocks2) + len(others)})-------\n"
+        text_keys1 = sorted(text_blocks_map1.keys())
+        for x in text_keys1:
+            text += f" TXT_ENC{x}: {len(text_blocks_map1[x])}\n"
+
+        text_keys2 = sorted(text_blocks_map2.keys())
+        for x in text_keys2:
+            text += f" TXT_ENC{x} [B]: {len(text_blocks_map2[x])}\n"
 
         for x in others:
             text += f" {x}\n"

inspire/prompt_support.py

@@ -18,15 +18,17 @@ from server import PromptServer
 from .libs import utils, common
 from .backend_support import CheckpointLoaderSimpleShared
 
+
+model_path = folder_paths.models_dir
+utils.add_folder_path_and_extensions("inspire_prompts", [os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "prompts"))], {'.txt'})
+
+
 prompt_builder_preset = {}
 
 
 resource_path = os.path.join(os.path.dirname(__file__), "..", "resources")
 resource_path = os.path.abspath(resource_path)
 
-prompts_path = os.path.join(os.path.dirname(__file__), "..", "prompts")
-prompts_path = os.path.abspath(prompts_path)
-
 
 try:
     pb_yaml_path = os.path.join(resource_path, 'prompt-builder.yaml')
@@ -44,9 +46,12 @@ except Exception as e:
 class LoadPromptsFromDir:
     @classmethod
     def INPUT_TYPES(cls):
-        global prompts_path
         try:
-            prompt_dirs = [d for d in os.listdir(prompts_path) if os.path.isdir(os.path.join(prompts_path, d))]
+            prompt_dirs = []
+            for x in folder_paths.get_folder_paths('inspire_prompts'):
+                for d in os.listdir(x):
+                    if os.path.isdir(os.path.join(x, d)):
+                        prompt_dirs.append(d)
         except Exception:
             prompt_dirs = []
 
@@ -55,83 +60,112 @@ class LoadPromptsFromDir:
                     },
                 "optional": {
                     "reload": ("BOOLEAN", { "default": False, "label_on": "if file changed", "label_off": "if value changed"}),
+                    "load_cap": ("INT", {"default": 0, "min": 0, "step": 1, "advanced": True, "tooltip": "The amount of prompts to load at once:\n0: Load all\n1 or higher: Load a specified number"}),
+                    "start_index": ("INT", {"default": 0, "min": -1, "step": 1, "max": 0xffffffffffffffff, "advanced": True, "tooltip": "Starting index for loading prompts:\n-1: The last prompt\n0 or higher: Load from the specified index"}),
                     }
                 }
 
-    RETURN_TYPES = ("ZIPPED_PROMPT",)
-    OUTPUT_IS_LIST = (True,)
+    RETURN_TYPES = ("ZIPPED_PROMPT", "INT", "INT")
+    RETURN_NAMES = ("zipped_prompt", "count", "remaining_count")
+    OUTPUT_IS_LIST = (True, False, False)
 
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Prompt"
 
     @staticmethod
-    def IS_CHANGED(prompt_dir, reload=False):
+    def IS_CHANGED(prompt_dir, reload=False, load_cap=0, start_index=-1):
         if not reload:
-            return prompt_dir
+            return prompt_dir, load_cap, start_index
         else:
-            global prompts_path
-            prompt_dir = os.path.join(prompts_path, prompt_dir)
-            files = [f for f in os.listdir(prompt_dir) if f.endswith(".txt")]
+            candidates = []
+            for d in folder_paths.get_folder_paths('inspire_prompts'):
+                candidates.append(os.path.join(d, prompt_dir))
+
+            prompt_files = []
+            for x in candidates:
+                for root, dirs, files in os.walk(x):
+                    for file in files:
+                        if file.endswith(".txt"):
+                            prompt_files.append(os.path.join(root, file))
+
+            prompt_files.sort()
 
             md5 = hashlib.md5()
-            files.sort()
 
-            for file in files:
-                md5.update(file.encode('utf-8'))
-                with open(os.path.join(prompt_dir, file), 'rb') as f:
+            for file_name in prompt_files:
+                md5.update(file_name.encode('utf-8'))
+                with open(folder_paths.get_full_path('inspire_prompts', file_name), 'rb') as f:
                     while True:
                         chunk = f.read(4096)
                         if not chunk:
                             break
                         md5.update(chunk)
 
-            return md5.hexdigest()
+            return md5.hexdigest(), load_cap, start_index
 
     @staticmethod
-    def doit(prompt_dir, reload=False):
-        global prompts_path
-        prompt_dir = os.path.join(prompts_path, prompt_dir)
-        files = [f for f in os.listdir(prompt_dir) if f.endswith(".txt")]
-        files.sort()
+    def doit(prompt_dir, reload=False, load_cap=0, start_index=-1):
+        candidates = []
+        for d in folder_paths.get_folder_paths('inspire_prompts'):
+            candidates.append(os.path.join(d, prompt_dir))
+
+        prompt_files = []
+        for x in candidates:
+            for root, dirs, files in os.walk(x):
+                for file in files:
+                    if file.endswith(".txt"):
+                        prompt_files.append(os.path.join(root, file))
+
+        prompt_files.sort()
 
         prompts = []
-        for file_name in files:
+        for file_name in prompt_files:
             print(f"file_name: {file_name}")
             try:
-                with open(os.path.join(prompt_dir, file_name), "r", encoding="utf-8") as file:
+                with open(file_name, "r", encoding="utf-8") as file:
                     prompt_data = file.read()
                     prompt_list = re.split(r'\n\s*-+\s*\n', prompt_data)
 
                     for prompt in prompt_list:
-                        pattern = r"positive:(.*?)(?:\n*|$)negative:(.*)"
+                        pattern = r"^(?:(?:positive:(?P<positive>.*?)|negative:(?P<negative>.*?)|name:(?P<name>.*?))\n*)+$"
                         matches = re.search(pattern, prompt, re.DOTALL)
 
                         if matches:
-                            positive_text = matches.group(1).strip()
-                            negative_text = matches.group(2).strip()
-                            result_tuple = (positive_text, negative_text, file_name)
+                            positive_text = matches.group('positive').strip()
+                            negative_text = matches.group('negative').strip()
+                            name_text = matches.group('name').strip() if matches.group('name') else file_name
+                            result_tuple = (positive_text, negative_text, name_text)
                             prompts.append(result_tuple)
                         else:
                             print(f"[WARN] LoadPromptsFromDir: invalid prompt format in '{file_name}'")
             except Exception as e:
                 print(f"[ERROR] LoadPromptsFromDir: an error occurred while processing '{file_name}': {str(e)}\nNOTE: Only files with UTF-8 encoding are supported.")
 
-        return (prompts, )
+        # slicing [start_index ~ start_index + load_cap]
+        total_prompts = len(prompts)
+        prompts = prompts[start_index:]
+        remaining_count = False
+        if load_cap > 0:
+            remaining_count = max(0, len(prompts) - load_cap)
+            prompts = prompts[:load_cap]
+
+        return prompts, total_prompts, remaining_count
 
 
 class LoadPromptsFromFile:
     @classmethod
     def INPUT_TYPES(cls):
-        global prompts_path
+        prompt_files = []
         try:
-            prompt_files = []
-            for root, dirs, files in os.walk(prompts_path):
-                for file in files:
-                    if file.endswith(".txt"):
-                        file_path = os.path.join(root, file)
-                        rel_path = os.path.relpath(file_path, prompts_path)
-                        prompt_files.append(rel_path)
+            prompts_paths = folder_paths.get_folder_paths('inspire_prompts')
+            for prompts_path in prompts_paths:
+                for root, dirs, files in os.walk(prompts_path):
+                    for file in files:
+                        if file.endswith(".txt"):
+                            file_path = os.path.join(root, file)
+                            rel_path = os.path.relpath(file_path, prompts_path)
+                            prompt_files.append(rel_path)
         except Exception:
             prompt_files = []
 
@@ -141,81 +175,114 @@ class LoadPromptsFromFile:
                 "optional": {
                         "text_data_opt": ("STRING", {"defaultInput": True}),
                         "reload": ("BOOLEAN", {"default": False, "label_on": "if file changed", "label_off": "if value changed"}),
+                        "load_cap": ("INT", {"default": 0, "min": 0, "step": 1, "advanced": True, "tooltip": "The amount of prompts to load at once:\n0: Load all\n1 or higher: Load a specified number"}),
+                        "start_index": ("INT", {"default": 0, "min": -1, "max": 0xffffffffffffffff, "step": 1, "advanced": True, "tooltip": "Starting index for loading prompts:\n-1: The last prompt\n0 or higher: Load from the specified index"}),
                         }
                 }
 
-    RETURN_TYPES = ("ZIPPED_PROMPT",)
-    OUTPUT_IS_LIST = (True,)
+    RETURN_TYPES = ("ZIPPED_PROMPT", "INT", "INT")
+    RETURN_NAMES = ("zipped_prompt", "count", "remaining_count")
+    OUTPUT_IS_LIST = (True, False, False)
 
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Prompt"
 
     @staticmethod
-    def IS_CHANGED(prompt_file, text_data_opt=None, reload=False):
+    def IS_CHANGED(prompt_file, text_data_opt=None, reload=False, load_cap=0, start_index=-1):
         md5 = hashlib.md5()
 
         if text_data_opt is not None:
             md5.update(text_data_opt)
-            return md5.hexdigest()
+            return md5.hexdigest(), load_cap, start_index
         elif not reload:
-            return prompt_file
+            return prompt_file, load_cap, start_index
         else:
-            prompt_path = os.path.join(prompts_path, prompt_file)
+            matched_path = None
+            for x in folder_paths.get_folder_paths('inspire_prompts'):
+                matched_path = os.path.join(x, prompt_file)
+                if not os.path.exists(matched_path):
+                    matched_path = None
+                else:
+                    break
 
-            with open(prompt_path, 'rb') as f:
+            if matched_path is None:
+                return float('NaN')
+
+            with open(matched_path, 'rb') as f:
                 while True:
                     chunk = f.read(4096)
                     if not chunk:
                         break
                     md5.update(chunk)
 
-            return md5.hexdigest()
+            return md5.hexdigest(), load_cap, start_index
 
     @staticmethod
-    def doit(prompt_file, text_data_opt=None, reload=False):
-        prompt_path = os.path.join(prompts_path, prompt_file)
+    def doit(prompt_file, text_data_opt=None, reload=False, load_cap=0, start_index=-1):
+        matched_path = None
+        for d in folder_paths.get_folder_paths('inspire_prompts'):
+            matched_path = os.path.join(d, prompt_file)
+            if os.path.exists(matched_path):
+                break
+            else:
+                matched_path = None
+
+        if matched_path:
+            print(f"[INFO] LoadPromptsFromFile: file found '{prompt_file}'")
+        else:
+            print(f"[WARN] LoadPromptsFromFile: file not found '{prompt_file}'")
 
         prompts = []
         try:
             if not text_data_opt:
-                with open(prompt_path, "r", encoding="utf-8") as file:
+                with open(matched_path, "r", encoding="utf-8") as file:
                     prompt_data = file.read()
             else:
                 prompt_data = text_data_opt
 
             prompt_list = re.split(r'\n\s*-+\s*\n', prompt_data)
 
-            pattern = r"positive:(.*?)(?:\n*|$)negative:(.*)"
+            pattern = r"^(?:(?:positive:(?P<positive>.*?)|negative:(?P<negative>.*?)|name:(?P<name>.*?))\n*)+$"
 
-            for prompt in prompt_list:
-                matches = re.search(pattern, prompt, re.DOTALL)
+            for p in prompt_list:
+                matches = re.search(pattern, p, re.DOTALL)
 
                 if matches:
-                    positive_text = matches.group(1).strip()
-                    negative_text = matches.group(2).strip()
-                    result_tuple = (positive_text, negative_text, prompt_file)
+                    positive_text = matches.group('positive').strip()
+                    negative_text = matches.group('negative').strip()
+                    name_text = matches.group('name').strip() if matches.group('name') else prompt_file
+                    result_tuple = (positive_text, negative_text, name_text)
                     prompts.append(result_tuple)
                 else:
                     print(f"[WARN] LoadPromptsFromFile: invalid prompt format in '{prompt_file}'")
         except Exception as e:
             print(f"[ERROR] LoadPromptsFromFile: an error occurred while processing '{prompt_file}': {str(e)}\nNOTE: Only files with UTF-8 encoding are supported.")
 
-        return (prompts, )
+        # slicing [start_index ~ start_index + load_cap]
+        total_prompts = len(prompts)
+        prompts = prompts[start_index:]
+        remaining_count = 0
+        if load_cap > 0:
+            remaining_count = max(0, len(prompts) - load_cap)
+            prompts = prompts[:load_cap]
+
+        return prompts, total_prompts, remaining_count
 
 
 class LoadSinglePromptFromFile:
     @classmethod
     def INPUT_TYPES(cls):
-        global prompts_path
+        prompt_files = []
         try:
-            prompt_files = []
-            for root, dirs, files in os.walk(prompts_path):
-                for file in files:
-                    if file.endswith(".txt"):
-                        file_path = os.path.join(root, file)
-                        rel_path = os.path.relpath(file_path, prompts_path)
-                        prompt_files.append(rel_path)
+            prompts_paths = folder_paths.get_folder_paths('inspire_prompts')
+            for prompts_path in prompts_paths:
+                for root, dirs, files in os.walk(prompts_path):
+                    for file in files:
+                        if file.endswith(".txt"):
+                            file_path = os.path.join(root, file)
+                            rel_path = os.path.relpath(file_path, prompts_path)
+                            prompt_files.append(rel_path)
         except Exception:
             prompt_files = []
 
@@ -235,7 +302,19 @@ class LoadSinglePromptFromFile:
 
     @staticmethod
     def doit(prompt_file, index, text_data_opt=None):
-        prompt_path = os.path.join(prompts_path, prompt_file)
+        prompt_path = None
+        prompts_paths = folder_paths.get_folder_paths('inspire_prompts')
+        for d in prompts_paths:
+            prompt_path = os.path.join(d, prompt_file)
+            if os.path.exists(prompt_path):
+                break
+            else:
+                prompt_path = None
+
+        if prompt_path:
+            print(f"[INFO] LoadSinglePromptFromFile: file found '{prompt_file}'")
+        else:
+            print(f"[WARN] LoadSinglePromptFromFile: file not found '{prompt_file}'")
 
         prompts = []
         try:
@@ -251,13 +330,14 @@ class LoadSinglePromptFromFile:
             except Exception:
                 prompt = prompt_list[-1]
 
-            pattern = r"positive:(.*?)(?:\n*|$)negative:(.*)"
+            pattern = r"^(?:(?:positive:(?P<positive>.*?)|negative:(?P<negative>.*?)|name:(?P<name>.*?))\n*)+$"
             matches = re.search(pattern, prompt, re.DOTALL)
 
             if matches:
-                positive_text = matches.group(1).strip()
-                negative_text = matches.group(2).strip()
-                result_tuple = (positive_text, negative_text, prompt_file)
+                positive_text = matches.group('positive').strip()
+                negative_text = matches.group('negative').strip()
+                name_text = matches.group('name').strip() if matches.group('name') else prompt_file
+                result_tuple = (positive_text, negative_text, name_text)
                 prompts.append(result_tuple)
             else:
                 print(f"[WARN] LoadSinglePromptFromFile: invalid prompt format in '{prompt_file}'")
@@ -497,7 +577,13 @@ class WildcardEncodeInspire:
                         "weight_interpretation": (["comfy", "A1111", "compel", "comfy++", "down_weight"], {'default': 'comfy++'}),
                         "wildcard_text": ("STRING", {"multiline": True, "dynamicPrompts": False, 'placeholder': 'Wildcard Prompt (User Input)'}),
                         "populated_text": ("STRING", {"multiline": True, "dynamicPrompts": False, 'placeholder': 'Populated Prompt (Will be generated automatically)'}),
-                        "mode": ("BOOLEAN", {"default": True, "label_on": "Populate", "label_off": "Fixed"}),
+
+                        "mode": (["populate", "fixed", "reproduce"], {"default": "populate", "tooltip":
+                            "populate: Before running the workflow, it overwrites the existing value of 'populated_text' with the prompt processed from 'wildcard_text'. In this mode, 'populated_text' cannot be edited.\n"
+                            "fixed: Ignores wildcard_text and keeps 'populated_text' as is. You can edit 'populated_text' in this mode.\n"
+                            "reproduce: This mode operates as 'fixed' mode only once for reproduction, and then it switches to 'populate' mode."
+                                                                               }),
+
                         "Select to add LoRA": (["Select the LoRA to add to the text"] + folder_paths.get_filename_list("loras"), ),
                         "Select to add Wildcard": (["Select the Wildcard to add to the text"],),
                         "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
@@ -538,7 +624,11 @@ class MakeBasicPipe:
                         "Add selection to": ("BOOLEAN", {"default": True, "label_on": "Positive", "label_off": "Negative"}),
                         "Select to add LoRA": (["Select the LoRA to add to the text"] + folder_paths.get_filename_list("loras"),),
                         "Select to add Wildcard": (["Select the Wildcard to add to the text"],),
-                        "wildcard_mode": ("BOOLEAN", {"default": True, "label_on": "Populate", "label_off": "Fixed"}),
+                        "wildcard_mode": (["populate", "fixed", "reproduce"], {"default": "populate", "tooltip":
+                            "populate: Before running the workflow, it overwrites the existing value of 'populated_text' with the prompt processed from 'wildcard_text'. In this mode, 'populated_text' cannot be edited.\n"
+                            "fixed: Ignores wildcard_text and keeps 'populated_text' as is. You can edit 'populated_text' in this mode.\n"
+                            "reproduce: This mode operates as 'fixed' mode only once for reproduction, and then it switches to 'populate' mode."
+                                                                               }),
 
                         "positive_populated_text": ("STRING", {"multiline": True, "dynamicPrompts": False, 'placeholder': 'Populated Positive Prompt (Will be generated automatically)'}),
                         "negative_populated_text": ("STRING", {"multiline": True, "dynamicPrompts": False, 'placeholder': 'Populated Negative Prompt (Will be generated automatically)'}),
@@ -623,11 +713,11 @@ class SeedExplorer:
             "optional":
                 {
                     "variation_method": (["linear", "slerp"],),
-                    "model": ("model",),
+                    "model": ("MODEL",),
                 }
         }
 
-    RETURN_TYPES = ("NOISE",)
+    RETURN_TYPES = ("NOISE_IMAGE",)
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Prompt"
@@ -702,15 +792,15 @@ class CompositeNoise:
     def INPUT_TYPES(s):
         return {
             "required": {
-                "destination": ("NOISE",),
-                "source": ("NOISE",),
+                "destination": ("NOISE_IMAGE",),
+                "source": ("NOISE_IMAGE",),
                 "mode": (["center", "left-top", "right-top", "left-bottom", "right-bottom", "xy"], ),
                 "x": ("INT", {"default": 0, "min": 0, "max": nodes.MAX_RESOLUTION, "step": 8}),
                 "y": ("INT", {"default": 0, "min": 0, "max": nodes.MAX_RESOLUTION, "step": 8}),
             },
         }
 
-    RETURN_TYPES = ("NOISE",)
+    RETURN_TYPES = ("NOISE_IMAGE",)
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Prompt"

inspire/regional_nodes.py

@@ -460,7 +460,7 @@ class RegionalSeedExplorerMask:
             "required": {
                 "mask": ("MASK",),
 
-                "noise": ("NOISE",),
+                "noise": ("NOISE_IMAGE",),
                 "seed_prompt": ("STRING", {"multiline": True, "dynamicPrompts": False, "pysssss.autocomplete": False}),
                 "enable_additional": ("BOOLEAN", {"default": True, "label_on": "true", "label_off": "false"}),
                 "additional_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
@@ -471,7 +471,7 @@ class RegionalSeedExplorerMask:
                 {"variation_method": (["linear", "slerp"],), }
         }
 
-    RETURN_TYPES = ("NOISE",)
+    RETURN_TYPES = ("NOISE_IMAGE",)
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Regional"
@@ -517,7 +517,7 @@ class RegionalSeedExplorerColorMask:
                 "color_mask": ("IMAGE",),
                 "mask_color": ("STRING", {"multiline": False, "default": "#FFFFFF"}),
 
-                "noise": ("NOISE",),
+                "noise": ("NOISE_IMAGE",),
                 "seed_prompt": ("STRING", {"multiline": True, "dynamicPrompts": False, "pysssss.autocomplete": False}),
                 "enable_additional": ("BOOLEAN", {"default": True, "label_on": "true", "label_off": "false"}),
                 "additional_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
@@ -528,7 +528,7 @@ class RegionalSeedExplorerColorMask:
                 {"variation_method": (["linear", "slerp"],), }
         }
 
-    RETURN_TYPES = ("NOISE", "MASK")
+    RETURN_TYPES = ("NOISE_IMAGE", "MASK")
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Regional"

js/lora_block_weight.js

@@ -34,19 +34,17 @@ app.registerExtension({
 
 			node._value = "Preset";
 
+            node.widgets[preset_i].callback = (v, canvas, node, pos, e) => {
+                node.widgets[vector_i].value = node._value.split(':')[1];
+                if(node.widgets_values) {
+                    node.widgets_values[vector_i] = node.widgets[preset_i].value;
+                }
+            }
+
 			Object.defineProperty(node.widgets[preset_i], "value", {
 				set: (value) => {
-				        const stackTrace = new Error().stack;
-                        if(stackTrace.includes('inner_value_change')) {
-                            if(value != "Preset") {
-                                node.widgets[vector_i].value = value.split(':')[1];
-	                            if(node.widgets_values) {
-	                                node.widgets_values[vector_i] = node.widgets[preset_i].value;
-                                }
-                            }
-                        }
-
-						node._value = value;
+				        if(value != "Preset")
+						    node._value = value;
 					},
 				get: () => {
                         return node._value;
@@ -77,86 +75,86 @@ app.registerExtension({
 		    let preset_i = 9;
 		    let vector_i = 10;
 			node._value = "Preset";
-			Object.defineProperty(node.widgets[preset_i], "value", {
-				set: (value) => {
-				        const stackTrace = new Error().stack;
-                        if(stackTrace.includes('inner_value_change')) {
-                            if(value != "Preset") {
-                                if(!value.startsWith('@') && node.widgets[vector_i].value != "")
-                                    node.widgets[vector_i].value += "\n";
-                                if(value.startsWith('@')) {
-                                    let spec = value.split(':')[1];
-                                    var n;
-                                    var sub_n = null;
-                                    var block = null;
 
-                                    if(isNaN(spec)) {
-                                        let sub_spec = spec.split(',');
+            node.widgets[preset_i].callback = (v, canvas, node, pos, e) => {
+                let value = node._value;
+                if(!value.startsWith('@') && node.widgets[vector_i].value != "")
+                    node.widgets[vector_i].value += "\n";
+                if(value.startsWith('@')) {
+                    let spec = value.split(':')[1];
+                    var n;
+                    var sub_n = null;
+                    var block = null;
 
-                                        if(sub_spec.length != 3) {
-	                                        node.widgets_values[vector_i] = '!! SPEC ERROR !!';
-	                                        node._value = '';
-	                                        return;
-                                        }
+                    if(isNaN(spec)) {
+                        let sub_spec = spec.split(',');
 
-                                        n = parseInt(sub_spec[0].trim());
-                                        sub_n = parseInt(sub_spec[1].trim());
-                                        block = parseInt(sub_spec[2].trim());
-                                    }
-                                    else {
-                                        n = parseInt(spec.trim());
-                                    }
-
-                                    node.widgets[vector_i].value = "";
-                                    if(sub_n == null) {
-                                        for(let i=1; i<=n; i++) {
-                                            var temp = "";
-                                            for(let j=1; j<=n; j++) {
-                                                if(temp!='')
-                                                    temp += ',';
-                                                if(j==i)
-                                                    temp += 'A';
-                                                else
-                                                    temp += '0';
-                                            }
-
-                                            node.widgets[vector_i].value += `B${i}:${temp}\n`;
-                                        }
-                                    }
-                                    else {
-                                        for(let i=1; i<=sub_n; i++) {
-                                            var temp = "";
-                                            for(let j=1; j<=n; j++) {
-                                                if(temp!='')
-                                                    temp += ',';
-
-                                                if(block!=j)
-                                                    temp += '0';
-                                                else {
-                                                    temp += ' ';
-                                                    for(let k=1; k<=sub_n; k++) {
-                                                        if(k==i)
-                                                            temp += 'A ';
-                                                        else
-                                                            temp += '0 ';
-                                                    }
-                                                }
-                                            }
-
-                                            node.widgets[vector_i].value += `B${block}.SUB${i}:${temp}\n`;
-                                        }
-                                    }
-                                }
-                                else {
-                                    node.widgets[vector_i].value += `${value}/${value.split(':')[0]}`;
-                                }
-	                            if(node.widgets_values) {
-	                                node.widgets_values[vector_i] = node.widgets[preset_i].value;
-                                }
-                            }
+                        if(sub_spec.length != 3) {
+                            node.widgets_values[vector_i] = '!! SPEC ERROR !!';
+                            node._value = '';
+                            return;
                         }
 
-						node._value = value;
+                        n = parseInt(sub_spec[0].trim());
+                        sub_n = parseInt(sub_spec[1].trim());
+                        block = parseInt(sub_spec[2].trim());
+                    }
+                    else {
+                        n = parseInt(spec.trim());
+                    }
+
+                    node.widgets[vector_i].value = "";
+                    if(sub_n == null) {
+                        for(let i=1; i<=n; i++) {
+                            var temp = "";
+                            for(let j=1; j<=n; j++) {
+                                if(temp!='')
+                                    temp += ',';
+                                if(j==i)
+                                    temp += 'A';
+                                else
+                                    temp += '0';
+                            }
+
+                            node.widgets[vector_i].value += `B${i}:${temp}\n`;
+                        }
+                    }
+                    else {
+                        for(let i=1; i<=sub_n; i++) {
+                            var temp = "";
+                            for(let j=1; j<=n; j++) {
+                                if(temp!='')
+                                    temp += ',';
+
+                                if(block!=j)
+                                    temp += '0';
+                                else {
+                                    temp += ' ';
+                                    for(let k=1; k<=sub_n; k++) {
+                                        if(k==i)
+                                            temp += 'A ';
+                                        else
+                                            temp += '0 ';
+                                    }
+                                }
+                            }
+
+                            node.widgets[vector_i].value += `B${block}.SUB${i}:${temp}\n`;
+                        }
+                    }
+                }
+                else {
+                    node.widgets[vector_i].value += `${value}/${value.split(':')[0]}`;
+                }
+                if(node.widgets_values) {
+                    node.widgets_values[vector_i] = node.widgets[preset_i].value;
+                }
+            }
+
+			Object.defineProperty(node.widgets[preset_i], "value", {
+				set: (value) => {
+				        if(value != 'Preset')
+						    node._value = value;
 					},
 				get: () => {
                         return node._value;

js/prompt.js

@@ -42,35 +42,38 @@ app.registerExtension({
 			// lora selector, wildcard selector
 			let combo_id = 5;
 
-			Object.defineProperty(node.widgets[combo_id], "value", {
-				set: (value) => {
-						const stackTrace = new Error().stack;
-						if(stackTrace.includes('inner_value_change')) {
-							if(value != "Select the LoRA to add to the text") {
-								let lora_name = value;
-								if (lora_name.endsWith('.safetensors')) {
-									lora_name = lora_name.slice(0, -12);
-								}
+			// lora
+            node.widgets[combo_id].callback = (value, canvas, node, pos, e) => {
+                let lora_name = node._value;
+                if(lora_name.endsWith('.safetensors')) {
+                    lora_name = lora_name.slice(0, -12);
+                }
 
-								wildcard_text_widget.value += `<lora:${lora_name}>`;
-							}
-						}
-					},
-				get: () => { return "Select the LoRA to add to the text"; }
-			});
+                wildcard_text_widget.value += `<lora:${lora_name}>`;
+            }
+
+            Object.defineProperty(node.widgets[combo_id], "value", {
+                set: (value) => {
+                        if (value !== "Select the LoRA to add to the text")
+                            node._value = value;
+                    },
+
+                get: () => { return "Select the LoRA to add to the text"; }
+            });
+
+            // wildcard
+            node.widgets[combo_id+1].callback = (value, canvas, node, pos, e) => {
+                    if(wildcard_text_widget.value != '')
+                        wildcard_text_widget.value += ', '
+
+                    wildcard_text_widget.value += node._wildcard_value;
+            }
 
 			Object.defineProperty(node.widgets[combo_id+1], "value", {
 				set: (value) => {
-						const stackTrace = new Error().stack;
-						if(stackTrace.includes('inner_value_change')) {
-							if(value != "Select the Wildcard to add to the text") {
-								if(wildcard_text_widget.value != '')
-									wildcard_text_widget.value += ', '
-
-								wildcard_text_widget.value += value;
-							}
-						}
-					},
+                    if (value !== "Select the Wildcard to add to the text")
+                        node._wildcard_value = value;
+                },
 				get: () => { return "Select the Wildcard to add to the text"; }
 			});
 
@@ -92,14 +95,20 @@ app.registerExtension({
 			// mode combo
 			Object.defineProperty(mode_widget, "value", {
 				set: (value) => {
-						node._mode_value = value == true || value == "Populate";
-						populated_text_widget.inputEl.disabled = value == true || value == "Populate";
+						if(value == true)
+							node._mode_value = "populate";
+						else if(value == false)
+							node._mode_value = "fixed";
+						else
+							node._mode_value = value; // combo value
+
+						populated_text_widget.inputEl.disabled = node._mode_value != 'populate';
 					},
 				get: () => {
 						if(node._mode_value != undefined)
 							return node._mode_value;
 						else
-							return true;
+							return 'populate';
 					 }
 			});
 		}
@@ -115,47 +124,46 @@ app.registerExtension({
 			// lora selector, wildcard selector
 			let combo_id = 5;
 
+            node.widgets[combo_id].callback = (value, canvas, node, pos, e) => {
+                let lora_name = node._lora_value;
+                if (lora_name.endsWith('.safetensors')) {
+                    lora_name = lora_name.slice(0, -12);
+                }
+
+                if(direction_widget.value) {
+                    pos_wildcard_text_widget.value += `<lora:${lora_name}>`;
+                }
+                else {
+                    neg_wildcard_text_widget.value += `<lora:${lora_name}>`;
+                }
+            }
 			Object.defineProperty(node.widgets[combo_id], "value", {
 				set: (value) => {
-						const stackTrace = new Error().stack;
-						if(stackTrace.includes('inner_value_change')) {
-							if(value != "Select the LoRA to add to the text") {
-								let lora_name = value;
-								if (lora_name.endsWith('.safetensors')) {
-									lora_name = lora_name.slice(0, -12);
-								}
-
-								if(direction_widget.value) {
-									pos_wildcard_text_widget.value += `<lora:${lora_name}>`;
-								}
-								else {
-									neg_wildcard_text_widget.value += `<lora:${lora_name}>`;
-								}
-							}
-						}
+                        if (value !== "Select the LoRA to add to the text")
+                            node._lora_value = value;
 					},
 				get: () => { return "Select the LoRA to add to the text"; }
 			});
 
+            node.widgets[combo_id+1].callback = (value, canvas, node, pos, e) => {
+                let w = null;
+                if(direction_widget.value) {
+                    w = pos_wildcard_text_widget;
+                }
+                else {
+                    w = neg_wildcard_text_widget;
+                }
+
+                if(w.value != '')
+                    w.value += ', '
+
+                w.value += node._wildcard_value;
+            }
+
 			Object.defineProperty(node.widgets[combo_id+1], "value", {
 				set: (value) => {
-						const stackTrace = new Error().stack;
-						if(stackTrace.includes('inner_value_change')) {
-							if(value != "Select the Wildcard to add to the text") {
-								let w = null;
-								if(direction_widget.value) {
-									w = pos_wildcard_text_widget;
-								}
-								else {
-									w = neg_wildcard_text_widget;
-								}
-
-								if(w.value != '')
-									w.value += ', '
-
-								w.value += value;
-							}
-						}
+                        if (value !== "Select the Wildcard to add to the text")
+                            node._wildcard_value = value;
 					},
 				get: () => { return "Select the Wildcard to add to the text"; }
 			});
@@ -178,15 +186,21 @@ app.registerExtension({
 			// mode combo
 			Object.defineProperty(mode_widget, "value", {
 				set: (value) => {
-						pos_populated_text_widget.inputEl.disabled = node._mode_value;
-						neg_populated_text_widget.inputEl.disabled = node._mode_value;
-						node._mode_value = value;
+						if(value == true)
+							node._mode_value = "populate";
+						else if(value == false)
+							node._mode_value = "fixed";
+						else
+							node._mode_value = value; // combo value
+
+						pos_populated_text_widget.inputEl.disabled = node._mode_value != 'populate';
+						neg_populated_text_widget.inputEl.disabled = node._mode_value != 'populate';
 					},
 				get: () => {
 						if(node._mode_value != undefined)
 							return node._mode_value;
 						else
-							return true;
+							return 'populate';
 					 }
 			});
 		}
@@ -205,24 +219,22 @@ app.registerExtension({
 				}
 			});
 
+            preset_widget.callback = (value, canvas, node, pos, e) => {
+                if(node.widgets[2].value) {
+                    node.widgets[2].value += ', ';
+                }
+
+                const y = node._preset_value.split(':');
+                if(y.length == 2)
+                    node.widgets[2].value += y[1].trim();
+                else
+                    node.widgets[2].value += node._preset_value.trim();
+            }
+
 			Object.defineProperty(preset_widget, "value", {
-				set: (x) => {
-					const stackTrace = new Error().stack;
-					if(stackTrace.includes('inner_value_change')) {
-						if(node.widgets[2].value) {
-							node.widgets[2].value += ', ';
-						}
-
-						const y = x.split(':');
-						if(y.length == 2)
-							node.widgets[2].value += y[1].trim();
-						else
-							node.widgets[2].value += x.trim();
-
-						if(node.widgets_values) {
-							node.widgets_values[2] = node.widgets[2].values;
-						}
-					};
+				set: (value) => {
+                    if (value !== "#PRESET")
+                        node._preset_value = value;
 				},
 				get: () => { return '#PRESET'; }
 			});

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "comfyui-inspire-pack"
-description = "This extension provides various nodes to support Lora Block Weight and the Impact Pack. Provides many easily applicable regional features and applications for Variation Seed."
-version = "1.5"
+description = "This extension provides various nodes to support Lora Block Weight, Regional Nodes, Backend Cache, Prompt Utils, List Utils, Noise(Seed) Utils, ... and the Impact Pack."
+version = "1.12.1"
 license = { file = "LICENSE" }
 dependencies = ["matplotlib", "cachetools"]