feat: Shared Diffusion Model Loader (Inspire)

feat: Shared Text Encoder Loader (Inspire)

https://github.com/ltdrdata/ComfyUI-Inspire-Pack/issues/205

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 * V0.69 incompatible with the outdated **ComfyUI IPAdapter Plus**.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.
@@ -143,7 +147,11 @@ 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.
@@ -154,8 +162,13 @@ 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:
@@ -179,3 +192,5 @@ 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, 6, 1]
+version_code = [1, 10]
 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/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
@@ -354,6 +355,21 @@ 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 +383,7 @@ 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/prompt_support.py

@@ -63,7 +63,8 @@ class LoadPromptsFromDir:
                     }
                 }
 
-    RETURN_TYPES = ("ZIPPED_PROMPT",)
+    RETURN_TYPES = ("ZIPPED_PROMPT", "INT")
+    RETURN_NAMES = ("zipped_prompt", "count")
     OUTPUT_IS_LIST = (True,)
 
     FUNCTION = "doit"
@@ -125,20 +126,21 @@ class LoadPromptsFromDir:
                     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, )
+        return (prompts, len(prompts),)
 
 
 class LoadPromptsFromFile:
@@ -166,7 +168,8 @@ class LoadPromptsFromFile:
                         }
                 }
 
-    RETURN_TYPES = ("ZIPPED_PROMPT",)
+    RETURN_TYPES = ("ZIPPED_PROMPT", "INT")
+    RETURN_NAMES = ("zipped_prompt", "count")
     OUTPUT_IS_LIST = (True,)
 
     FUNCTION = "doit"
@@ -208,12 +211,14 @@ class LoadPromptsFromFile:
         matched_path = None
         for d in folder_paths.get_folder_paths('inspire_prompts'):
             matched_path = os.path.join(d, prompt_file)
-            if not os.path.exists(matched_path):
-                matched_path = None
-            else:
+            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 = []
@@ -226,22 +231,23 @@ class LoadPromptsFromFile:
 
             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 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, )
+        return (prompts, len(prompts),)
 
 
 class LoadSinglePromptFromFile:
@@ -286,6 +292,8 @@ class LoadSinglePromptFromFile:
                 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 = []
@@ -302,13 +310,14 @@ 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}'")
@@ -678,7 +687,7 @@ class SeedExplorer:
                 }
         }
 
-    RETURN_TYPES = ("NOISE",)
+    RETURN_TYPES = ("NOISE_IMAGE",)
     FUNCTION = "doit"
 
     CATEGORY = "InspirePack/Prompt"
@@ -753,15 +762,15 @@ 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"; }
 			});
 
@@ -115,47 +118,46 @@ 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"; }
 			});
@@ -205,24 +207,22 @@ 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 = "1.6.1"
+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 = "1.10"
 license = { file = "LICENSE" }
 dependencies = ["matplotlib", "cachetools"]