v0.14.0

发布新节点splitImage & gridoutput，用于分割图片和随机摆放元素修复若干bug
add splitImage&gridoutput
2024-01-20 21:43:18 +08:00 · 2024-01-20 17:39:53 +08:00 · 2024-01-19 09:45:03 +08:00 · 2024-01-18 22:49:13 +08:00 · 2024-01-18 12:45:29 +08:00 · 2024-01-18 11:12:03 +08:00
38 changed files with 3980 additions and 1142 deletions
@@ -31,7 +31,7 @@ APP-JSON:

 > 暂时支持8种节点作为界面上的输入节点：Load Image、CLIPTextEncode、PromptSlide、TextInput_、Color、FloatSlider、IntNumber、CheckpointLoaderSimple、LoraLoader

-> 输出节点：PreviewImage 、SaveImage、ShowTextForGPT、VHS_VideoCombine
+> 输出节点：PreviewImage 、SaveImage、ShowTextForGPT、VHS_VideoCombine、PromptImage

 > seed统一输入控件，支持：SamplerCustom、KSampler

@@ -67,7 +67,7 @@ https://github.com/shadowcz007/comfyui-mixlab-nodes/assets/12645064/e7e77f90-e43
 > PromptSlide
 ![](./assets/prompt_weight.png)

-![](./workflow/promptslide-appinfo-workflow.svg)
+<!-- ![](./workflow/promptslide-appinfo-workflow.svg) -->

 > randomPrompt

@@ -79,6 +79,10 @@ https://github.com/shadowcz007/comfyui-mixlab-nodes/assets/12645064/e7e77f90-e43

 > PromptImage & PromptSimplification,Assist in simplifying prompt words, comparing images and prompt word nodes.

+> ChinesePrompt && PromptGenerate，中文prompt节点，直接用中文书写你的prompt
+
+![](./assets/ChinesePrompt_workflow.svg)
+

 ### Layers
 > A new layer class node has been added, allowing you to separate the image into layers. After merging the images, you can input the controlnet for further processing.
@@ -159,23 +163,19 @@ An improvement has been made to directly redirect to GitHub to search for missin
 ![node-not-found](./assets/node-not-found.png)


-### Update 
-v0.8.0 🚀🚗🚚🏃‍ LaMaInpainting
- 新增 LaMaInpainting
- 优化color节点的输出
- 修复高清显示屏上定位节点不准的情况
-
- Add LaMaInpainting
- Optimize the output of the color node
- Fix the issue of inaccurate positioning node on high-definition display screens
-
-
 ### Models
+
+[Download rembg Models](https://github.com/danielgatis/rembg/tree/main#Models),move to:models/rembg
+
 [Download CLIPSeg](https://huggingface.co/CIDAS/clipseg-rd64-refined/tree/main), move to : models/clipseg

 [Download lama](https://github.com/enesmsahin/simple-lama-inpainting/releases/download/v0.1.0/big-lama.pt), move to : models/lama

-[Download Salesforce\blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base), move to : models/clip_interrogator/Salesforce/blip-image-captioning-base
+[Download Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base), move to : models/clip_interrogator/Salesforce/blip-image-captioning-base
+
+[Download succinctly/text2image-prompt-generator](https://huggingface.co/succinctly/text2image-prompt-generator/tree/main),move to:prompt_generator/text2image-prompt-generator
+
+[Download Helsinki-NLP/opus-mt-zh-en](https://huggingface.co/Helsinki-NLP/opus-mt-zh-en/tree/main),move to:prompt_generator/opus-mt-zh-en

 ## Installation

@@ -216,9 +216,6 @@ pip3 install -r requirements.txt
 #### discussions:
 [discussions](https://github.com/shadowcz007/comfyui-mixlab-nodes/discussions)

-### TODO:
- 音频播放节点：带可视化、支持多音轨、可配置音轨音量
- vector https://github.com/GeorgLegato/stable-diffusion-webui-vectorstudio


 <picture>
@@ -192,7 +192,7 @@ def read_workflow_json_files(folder_path ):
 def get_workflows():
    # print("#####path::", current_path)
    workflow_path=os.path.join(current_path, "workflow")
-    print('workflow_path: ',workflow_path)
+    # print('workflow_path: ',workflow_path)
    if not os.path.exists(workflow_path):
        # 使用mkdir()方法创建新目录
        os.mkdir(workflow_path)
@@ -231,8 +231,14 @@ def get_my_workflow_for_app(filename="my_workflow_app.json",category="",is_all=F
                    })
                else:
                    category=''
+                    input=None
+                    output=None
                    if 'category' in x['app']:
                        category=x['app']['category']
+                    if 'input' in x['app']:
+                        input=x['app']['input']
+                    if 'output' in x['app']:
+                        output=x['app']['output']
                    apps.append({
                        "filename":item["filename"],
                        "category":category,
@@ -244,6 +250,8 @@ def get_my_workflow_for_app(filename="my_workflow_app.json",category="",is_all=F
                                "icon":(x['app']['icon'] if 'icon' in x['app'] else None),
                                "name":x['app']['name'],
                                "version":x['app']['version'],
+                                "input":input,
+                                "output":output
                            }
                        },
                        "date":item["date"]
@@ -271,8 +279,14 @@ def get_my_workflow_for_app(filename="my_workflow_app.json",category="",is_all=F
                # print(apps[0]['filename'] ,item["filename"])
                if apps[0]['filename']!=item["filename"]:
                    category=''
+                    input=None
+                    output=None
                    if 'category' in x['app']:
                        category=x['app']['category']
+                    if 'input' in x['app']:
+                        input=x['app']['input']
+                    if 'output' in x['app']:
+                        output=x['app']['output']
                    apps.append({
                        "filename":item["filename"],
                        # "category":category,
@@ -284,6 +298,8 @@ def get_my_workflow_for_app(filename="my_workflow_app.json",category="",is_all=F
                                "icon":(x['app']['icon'] if 'icon' in x['app'] else None),
                                "name":x['app']['name'],
                                "version":x['app']['version'],
+                                "input":input,
+                                "output":output
                            }
                        },
                        "date":item["date"]
@@ -503,6 +519,11 @@ async def nodes_map_hander(request):
 # 把插件自定义的路由添加到comfyui server里
 def new_add_routes(self):
        import nodes
+        try:
+            self.user_manager.add_routes(self.routes)
+        except:
+            print('pls update')
+        
        self.app.add_routes(routes)
        self.app.add_routes(self.routes)
        for name, dir in nodes.EXTENSION_WEB_DIRS.items():
@@ -529,26 +550,28 @@ PromptServer.add_routes=new_add_routes


 # 导入节点
-from .nodes.PromptNode import RandomPrompt,PromptSlide,PromptSimplification,PromptImage
-from .nodes.ImageNode import NoiseImage,TransparentImage,GradientImage,LoadImagesFromPath,LoadImagesFromURL,ResizeImage,TextImage,SvgImage,Image3D,ShowLayer,NewLayer,MergeLayers,AreaToMask,SmoothMask,FeatheredMask,SplitLongMask,ImageCropByAlpha,EnhanceImage,FaceToMask
+from .nodes.PromptNode import EmbeddingPrompt,RandomPrompt,PromptSlide,PromptSimplification,PromptImage,JoinWithDelimiter
+from .nodes.ImageNode import SplitImage,GridOutput,GetImageSize_,MirroredImage,ImageColorTransfer,NoiseImage,TransparentImage,GradientImage,LoadImagesFromPath,LoadImagesFromURL,ResizeImage,TextImage,SvgImage,Image3D,ShowLayer,NewLayer,MergeLayers,AreaToMask,SmoothMask,SplitLongMask,ImageCropByAlpha,EnhanceImage,FaceToMask
 from .nodes.Vae import VAELoader,VAEDecode
 from .nodes.ScreenShareNode import ScreenShareNode,FloatingVideo
 from .nodes.Clipseg import CLIPSeg,CombineMasks
 from .nodes.ChatGPT import ChatGPTNode,ShowTextForGPT,CharacterInText
 from .nodes.Audio import GamePal,SpeechRecognition,SpeechSynthesis
-from .nodes.Utils import AppInfo,IntNumber,FloatSlider,TextInput,ColorInput,FontInput,TextToNumber,DynamicDelayProcessor,LimitNumber,SwitchByIndex,GetImageSize_,MultiplicationNode
-from .nodes.Lama import LaMaInpainting
-from .nodes.ClipInterrogator import ClipInterrogator
+from .nodes.Utils import TESTNODE_,AppInfo,IntNumber,FloatSlider,TextInput,ColorInput,FontInput,TextToNumber,DynamicDelayProcessor,LimitNumber,SwitchByIndex,MultiplicationNode
+from .nodes.Mask import OutlineMask,FeatheredMask
+

 # 要导出的所有节点及其名称的字典
 # 注意：名称应全局唯一
 NODE_CLASS_MAPPINGS = {
    "AppInfo":AppInfo,
+    "TESTNODE_":TESTNODE_,
    "RandomPrompt":RandomPrompt,
+    "EmbeddingPrompt":EmbeddingPrompt,
    "PromptSlide":PromptSlide,
    "PromptSimplification":PromptSimplification,
    "PromptImage":PromptImage,
-    "ClipInterrogator":ClipInterrogator,
+    "MirroredImage":MirroredImage,
    "NoiseImage":NoiseImage,
    "GradientImage":GradientImage,
    "TransparentImage":TransparentImage,
@@ -559,8 +582,11 @@ NODE_CLASS_MAPPINGS = {
    "EnhanceImage":EnhanceImage,
    "SvgImage":SvgImage,
    "3DImage":Image3D, 
+    "ImageColorTransfer":ImageColorTransfer,
    "ShowLayer":ShowLayer,
    "NewLayer":NewLayer,
+    "SplitImage":SplitImage,
+    "GridOutput":GridOutput,
    "MergeLayers":MergeLayers,
    "SplitLongMask":SplitLongMask,
    "FeatheredMask":FeatheredMask,
@@ -590,7 +616,9 @@ NODE_CLASS_MAPPINGS = {
    "GetImageSize_":GetImageSize_,
    "SwitchByIndex":SwitchByIndex,
    "LimitNumber":LimitNumber, 
-    "LaMaInpainting":LaMaInpainting
+    "OutlineMask":OutlineMask,
+    "JoinWithDelimiter":JoinWithDelimiter
+    # "LaMaInpainting":LaMaInpainting
    # "GamePal":GamePal
 }

@@ -612,14 +640,52 @@ NODE_DISPLAY_NAME_MAPPINGS = {
    "3DImage":"3DImage ♾️Mixlab",
    "DynamicDelayProcessor":"DynamicDelayByText ♾️Mixlab",
    "LaMaInpainting":"LaMaInpainting ♾️Mixlab",
-    "PromptSlide":"PromptSlide ♾️Mixlab"
-
-    # "GamePal":"GamePal ♾️Mixlab"
+    "PromptSlide":"PromptSlide ♾️Mixlab",
+    "PromptGenerate_Mix":"PromptGenerate ♾️Mixlab",
+    "ChinesePrompt_Mix":"ChinesePrompt ♾️Mixlab",
+    "GamePal":"GamePal ♾️Mixlab",
+    "RembgNode_Mix":"Removebg"
 }

 # web ui的节点功能
 WEB_DIRECTORY = "./web"

 print('--------------')
-print('\033[91m ### Mixlab Nodes: \033[93mLoaded\033[0m')
-print('--------------')
+print('\033[91m ### Mixlab Nodes: \033[93mLoaded')
+
+try:
+    from .nodes.Lama import LaMaInpainting
+    print('LaMaInpainting.available',LaMaInpainting.available)
+    if LaMaInpainting.available:
+        NODE_CLASS_MAPPINGS['LaMaInpainting']=LaMaInpainting
+except Exception as e:
+    print('LaMaInpainting.available',False,e)
+
+try:
+    from .nodes.ClipInterrogator import ClipInterrogator
+    print('ClipInterrogator.available',ClipInterrogator.available)
+    if ClipInterrogator.available:
+        NODE_CLASS_MAPPINGS['ClipInterrogator']=ClipInterrogator
+except Exception as e:
+    print('ClipInterrogator.available',False,e)
+
+try:
+    from .nodes.TextGenerateNode import PromptGenerate,ChinesePrompt
+    print('PromptGenerate.available',PromptGenerate.available)
+    if PromptGenerate.available:
+        NODE_CLASS_MAPPINGS['PromptGenerate_Mix']=PromptGenerate
+    print('ChinesePrompt.available',ChinesePrompt.available)
+    if ChinesePrompt.available:
+        NODE_CLASS_MAPPINGS['ChinesePrompt_Mix']=ChinesePrompt
+except Exception as e:
+    print('TextGenerateNode.available',False,e)
+
+try:
+    from .nodes.RembgNode import RembgNode_
+    print('RembgNode_.available',RembgNode_.available)
+    if RembgNode_.available:
+        NODE_CLASS_MAPPINGS['RembgNode_Mix']=RembgNode_
+except Exception as e:
+    print('RembgNode_.available',False,e)
+
+print('\033[93m -------------- \033[0m')
@@ -0,0 +1,30 @@
+Elegant evening gown
+Casual jeans and t-shirt
+Formal black suit
+Stylish leather jacket
+Flowy bohemian dress
+Sporty tracksuit
+Chic little black dress
+Trendy ripped jeans
+Classic white button-down shirt
+Cozy oversized sweater
+Sophisticated tailored blazer
+Quirky patterned leggings
+Striped sailor top
+Polished knee-length skirt
+Vintage-inspired floral dress
+Edgy motorcycle jacket
+Preppy polo shirt
+Boho maxi skirt
+Professional pinstripe suit
+Relaxed denim shorts
+Glamorous sequined dress
+Athletic running shoes
+Formal bow tie
+Casual baseball cap
+Stylish fedora hat
+Warm woolen scarf
+Comfortable cotton socks
+Trendy ankle boots
+Cute summer sandals
+Cozy pajama set
@@ -0,0 +1,30 @@
+Happy
+Sad
+Angry
+Surprised
+Excited
+Worried
+Confused
+Disgusted
+Amused
+Bored
+Curious
+Embarrassed
+Frustrated
+Nervous
+Pleased
+Relieved
+Shy
+Tired
+Serious
+Silly
+Proud
+Grumpy
+Smug
+Sarcastic
+Flirty
+Skeptical
+Shocked
+Blissful
+Envious
+Mischievous
@@ -4761,12 +4761,18 @@
    ],
    "https://github.com/shadowcz007/comfyui-mixlab-nodes": [
        [
+            "GridOutput",
+            "SplitImage",
+            "PromptGenerate_Mix",
+            "JoinWithDelimiter",
+            "ChinesePrompt_Mix",
            "3DImage",
            "AppInfo",
            "IntNumber",
            "FloatSlider",
            "ResizeImage",
            "NoiseImage",
+            "PromptImage",
            "AreaToMask",
            "CLIPSeg_",
            "CharacterInText",
@@ -0,0 +1,101 @@
+Doctor
+Teacher
+Engineer
+Lawyer
+Accountant
+Nurse
+Architect
+Chef
+Pilot
+Scientist
+Artist
+Writer
+Musician
+Actor
+Photographer
+Police officer
+Firefighter
+Dentist
+Pharmacist
+Veterinarian
+Electrician
+Plumber
+Carpenter
+Mechanic
+Farmer
+Astronaut
+Athlete
+Journalist
+Politician
+Economist
+Psychologist
+Social worker
+Librarian
+Translator
+Salesperson
+Entrepreneur
+Financial advisor
+Graphic designer
+Web developer
+Marketing manager
+Human resources manager
+Project manager
+Event planner
+Fashion designer
+Interior decorator
+Real estate agent
+Archaeologist
+Biologist
+Chemist
+Geologist
+Physicist
+Mathematician
+Historian
+Geographer
+Economist
+Sociologist
+Anthropologist
+Archaeologist
+Linguist
+Philosopher
+Economist
+Sociologist
+Anthropologist
+Archaeologist
+Linguist
+Philosopher
+Geographer
+Historian
+Economist
+Sociologist
+Anthropologist
+Archaeologist
+Linguist
+Philosopher
+Geographer
+Historian
+Economist
+Sociologist
+Anthropologist
+Archaeologist
+Linguist
+Philosopher
+Geographer
+Historian
+Economist
+Sociologist
+Anthropologist
+Archaeologist
+Linguist
+Philosopher
+Geographer
+Historian
+Economist
+Sociologist
+Anthropologist
+Archaeologist
+Linguist
+Philosopher
+Geographer
+Historian
+                     #MixCopilot
@@ -0,0 +1,58 @@
+Residential space
+Apartment building
+Villa
+Bungalow
+Condominium
+Commercial space
+Shopping mall
+Supermarket
+Restaurant
+Store
+Market
+Office space
+Office building
+Office
+Meeting room
+Co-working space
+Educational space
+School
+University
+Training institution
+Library
+Laboratory
+Medical space
+Hospital
+Clinic
+Pharmacy
+Nursing home
+Rehabilitation center
+Cultural space
+Museum
+Library
+Theater
+Concert hall
+Gallery
+Sports space
+Sports stadium
+Gym
+Swimming pool
+Basketball court
+Football field
+Transportation space
+Airport
+Train station
+Subway station
+Bus stop
+Parking lot
+Public space
+Park
+Square
+Street
+Pedestrian street
+Community center
+Industrial space
+Factory
+Warehouse
+Production workshop
+Mine
+Power plant
@@ -24,7 +24,7 @@ class SpeechRecognition:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/audio"
+    CATEGORY = "♾️Mixlab/Audio"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -48,7 +48,7 @@ class SpeechSynthesis:
    OUTPUT_NODE = True
    OUTPUT_IS_LIST = (True,)

-    CATEGORY = "♾️Mixlab/audio"
+    CATEGORY = "♾️Mixlab/Audio"

    def run(self, text):
        # print(session_history)
@@ -82,7 +82,7 @@ class GamePal:
    OUTPUT_NODE = True
    OUTPUT_IS_LIST = (False,)

-    CATEGORY = "♾️Mixlab/audio"
+    CATEGORY = "♾️Mixlab/Audio"

    def run(self, input_text,input_num,python_code):
        exec(python_code)
@@ -1,15 +1,61 @@
-import os
+import os,sys
 import folder_paths

 from PIL import Image
+import importlib.util
+
 import comfy.utils
 import numpy as np
 import json
 import torch
+import random
+
+
+# from clip_interrogator import Config, Interrogator
+
+
+global _available
+_available=False
+
+def is_installed(package):
+    try:
+        spec = importlib.util.find_spec(package)
+    except ModuleNotFoundError:
+        return False
+    return spec is not None
+
+
+try:
+    if is_installed('clip_interrogator')==False:
+        import subprocess
+
+        # 安装
+        print('#pip install clip-interrogator==0.6.0')
+
+        result = subprocess.run([sys.executable, '-s', '-m', 'pip', 'install', 'clip-interrogator==0.6.0'], capture_output=True, text=True)
+
+        #检查命令执行结果
+        if result.returncode == 0:
+            print("#install success")
+            from clip_interrogator import Config, Interrogator
+            _available=True
+        else:
+            print("#install error")
+        
+    else:
+        from clip_interrogator import Config, Interrogator
+        _available=True
+
+except:
+    _available=False
+
+try:
+    from transformers import AutoProcessor, BlipForConditionalGeneration
+except:
+    _available=False
+    print('pls check  transformers.__version__>=4.36.0:: AutoProcessor, BlipForConditionalGeneration')

-from transformers import AutoProcessor, BlipForConditionalGeneration

-from clip_interrogator import Config, Interrogator

 def load_caption_model(model_path,config,t='blip-base'):
    dtype=torch.float16 if config.device == 'cuda' else torch.float32
@@ -28,11 +74,11 @@ def load_caption_model(model_path,config,t='blip-base'):
 caption_model_path=os.path.join(folder_paths.models_dir, "clip_interrogator/Salesforce/blip-image-captioning-base")
 if not os.path.exists(caption_model_path):
    print(f"## clip_interrogator_model not found: {caption_model_path}, pls download from https://huggingface.co/Salesforce/blip-image-captioning-base")
+    caption_model_path='Salesforce/blip-image-captioning-base'

 cache_path=os.path.join(folder_paths.models_dir, "clip_interrogator")


-
 # Tensor to PIL
 def tensor2pil(image):
    return Image.fromarray(np.clip(255. * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8))
@@ -58,7 +104,53 @@ def image_analysis_fn(ci,image):
    trending_ranks = {trending: sim for trending, sim in zip(top_trendings, ci.similarities(image_features, top_trendings))}
    flavor_ranks = {flavor: sim for flavor, sim in zip(top_flavors, ci.similarities(image_features, top_flavors))}
    
-    return medium_ranks, artist_ranks, movement_ranks, trending_ranks, flavor_ranks
+    return {
+        "medium_ranks":medium_ranks, 
+        "artist_ranks":artist_ranks, 
+        "movement_ranks":movement_ranks, 
+        "trending_ranks":trending_ranks, 
+        "flavor_ranks":flavor_ranks
+        }
+
+
+def generate_sentences(data):
+    sentences = []
+
+    # Get the length of data
+    data_length = len(data)
+
+    # Use a recursive function to handle variable-length data
+    def generate_recursive(index, current_sentence, current_score):
+        # Check if recursion is complete
+        if index == data_length:
+            sentences.append({"sentence": current_sentence, "score": current_score})
+            return
+
+        # Get the current level data
+        current_data = data[index]
+
+        # Iterate through the current level data
+        for phrase in current_data:
+            sentence = current_sentence + ("," if current_sentence.strip() else "") + phrase
+            score = current_score + current_data[phrase]
+            generate_recursive(index + 1, sentence, score)
+
+    # Start recursive generation of sentences
+    generate_recursive(0, "", 0)
+
+    # Sort the generated sentences by score in descending order
+    sentences.sort(key=lambda x: x["score"], reverse=True)
+
+    def get_random_elements(elements, num):
+        return random.sample(elements, num)
+
+    ps = get_random_elements(sentences, 5)
+    ps = [s["sentence"] for s in sorted(ps, key=lambda x: x["score"], reverse=True)]
+
+    return ps
+
+
+

 def image_to_prompt(ci,image, mode):
    ci.config.chunk_size = 2048 if ci.config.clip_model_name == "ViT-L-14/openai" else 1024
@@ -79,6 +171,10 @@ def image_to_prompt(ci,image, mode):


 class ClipInterrogator:
+
+    global _available
+    available=_available
+    
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {
@@ -86,17 +182,22 @@ class ClipInterrogator:
            "prompt_mode": (['fast','classic','best','negative'],),
            "image_analysis": (["off","on"],), 
                             },
+
+                # "optional":{
+                #     "output":("CLIPINTERROGATOR", {"multiline": True,"default": "", "dynamicPrompts": False})
+                # },
+
                }
    
-    RETURN_TYPES = ("STRING",)
-    RETURN_NAMES = ("prompt",)
+    RETURN_TYPES = ("STRING","STRING",)
+    RETURN_NAMES = ("prompt","random_samples",)

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/prompt"
+    CATEGORY = "♾️Mixlab/Prompt"
    OUTPUT_NODE = True
    INPUT_IS_LIST = True
-    OUTPUT_IS_LIST = (True,)
+    OUTPUT_IS_LIST = (True,True,)
    global ci
    ci = None
    def run(self,image,prompt_mode,image_analysis):
@@ -156,5 +257,21 @@ class ClipInterrogator:
            ci.caption_offloaded = True

        # analysis_result=[]
+        # items = app.graph.getNodeById(31).widgets[2].value["items"]
+        
+        random_samples=[]

-        return {"ui":{"prompt": prompt_result,"analysis":analysis_result},"result": (prompt_result,)}
+        for r in analysis_result:
+            random_sample = generate_sentences([r['medium_ranks'], r['artist_ranks'],r['movement_ranks'],r['trending_ranks'],r['flavor_ranks']])
+            for s in random_sample:
+                random_samples.append(s)
+        # print(len(random_samples))
+        # print('-----')
+        # print( random_samples)
+        return {
+            "ui":{
+                    "prompt": prompt_result,
+                    "analysis":analysis_result,
+                    "random_samples":random_samples
+                },
+            "result": (prompt_result,random_samples,)}
@@ -106,13 +106,13 @@ class CLIPSeg:
                     },
                "optional":
                    {
-                        "blur": ("FLOAT", {"min": 0, "max": 15, "step": 0.1, "default": 7}),
-                        "threshold": ("FLOAT", {"min": 0, "max": 1, "step": 0.05, "default": 0.4}),
+                        "blur": ("FLOAT", {"min": 0, "max": 15, "step": 0.1, "default": 3}),
+                        "threshold": ("FLOAT", {"min": 0, "max": 1, "step": 0.05, "default": 0.3}),
                        "dilation_factor": ("INT", {"min": 0, "max": 10, "step": 1, "default": 4}),
                    }
                }

-    CATEGORY = "♾️Mixlab/mask"
+    CATEGORY = "♾️Mixlab/Mask"
    RETURN_TYPES = ("MASK", "IMAGE", "IMAGE",)
    RETURN_NAMES = ("Mask","Heatmap Mask", "BW Mask")

@@ -218,7 +218,7 @@ class CombineMasks:
                    },
                }
        
-    CATEGORY = "♾️Mixlab/mask"
+    CATEGORY = "♾️Mixlab/Mask"
    RETURN_TYPES = ("MASK", "IMAGE", "IMAGE",)
    RETURN_NAMES = ("Combined Mask","Heatmap Mask", "BW Mask")

@@ -10,10 +10,12 @@ import folder_paths
 import json,io
 from comfy.cli_args import args
 import cv2 
-
+import math
 from .Watcher import FolderWatcher


+
+
 FONT_PATH= os.path.abspath(os.path.join(os.path.dirname(__file__),'../assets/王汉宗颜楷体繁.ttf'))

 MAX_RESOLUTION=8192
@@ -27,6 +29,94 @@ def pil2tensor(image):
    return torch.from_numpy(np.array(image).astype(np.float32) / 255.0).unsqueeze(0)


+# 颜色迁移
+# Color-Transfer-between-Images https://github.com/chia56028/Color-Transfer-between-Images/blob/master/color_transfer.py
+
+def get_mean_and_std(x):
+	x_mean, x_std = cv2.meanStdDev(x)
+	x_mean = np.hstack(np.around(x_mean,2))
+	x_std = np.hstack(np.around(x_std,2))
+	return x_mean, x_std
+
+def color_transfer(source,target):
+	# sources = ['s1','s2','s3','s4','s5','s6']
+	# targets = ['t1','t2','t3','t4','t5','t6']
+
+     # 将PIL的Image类型转换为OpenCV的numpy数组
+    source = cv2.cvtColor(np.array(source), cv2.COLOR_RGB2LAB)
+    target = cv2.cvtColor(np.array(target), cv2.COLOR_RGB2LAB)
+
+    s_mean, s_std = get_mean_and_std(source)
+    t_mean, t_std = get_mean_and_std(target)
+
+    height, width, channel = source.shape
+	
+    for i in range(0,height):
+        for j in range(0,width):
+            for k in range(0,channel):
+                x = source[i,j,k]
+                x = ((x-s_mean[k])*(t_std[k]/s_std[k]))+t_mean[k]
+				# round or +0.5
+                x = round(x)
+				# boundary check
+                x = 0 if x<0 else x
+                x = 255 if x>255 else x
+                source[i,j,k] = x
+    
+    source = cv2.cvtColor(source,cv2.COLOR_LAB2RGB)
+ 
+    # 创建PIL图像对象
+    image_pil = Image.fromarray(source)
+    
+    return image_pil
+
+
+
+# 组合
+def create_big_image(image_folder, image_count):
+    # 计算行数和列数
+    rows = math.ceil(math.sqrt(image_count))
+    cols = math.ceil(image_count / rows)
+
+    # 获取每个小图的尺寸
+    small_width = 100
+    small_height = 100
+
+    # 计算大图的尺寸
+    big_width = small_width * cols
+    big_height = small_height * rows
+
+    # 创建一个新的大图
+    big_image = Image.new('RGB', (big_width, big_height))
+
+    # 获取所有图片文件的路径
+    image_files = [f for f in os.listdir(image_folder) if os.path.isfile(os.path.join(image_folder, f))]
+
+    # 遍历所有图片文件
+    for i, image_file in enumerate(image_files):
+        # 打开图片并调整大小
+        image = Image.open(os.path.join(image_folder, image_file))
+        image = image.resize((small_width, small_height))
+
+        # 计算当前小图的位置
+        row = i // cols
+        col = i % cols
+        x = col * small_width
+        y = row * small_height
+
+        # 将小图粘贴到大图上
+        big_image.paste(image, (x, y))
+
+    return big_image
+
+# # 调用方法并保存大图
+# image_folder = 'path/to/folder/containing/images'
+# image_count = 100
+# big_image = create_big_image(image_folder, image_count)
+# big_image.save('path/to/save/big_image.jpg')
+
+
+
 def naive_cutout(img, mask,invert=True):
    """
    Perform a simple cutout operation on an image using a mask.
@@ -203,6 +293,11 @@ def generate_gradient_image(width, height, start_color_hex, end_color_hex):
 # gradient_image = generate_gradient_image(width, height, start_color_hex, end_color_hex)
 # gradient_image.save('gradient_image.png')

+def rgb_to_hex(rgb):
+    r, g, b = rgb
+    hex_color = "#{:02x}{:02x}{:02x}".format(r, g, b)
+    return hex_color
+

 # 读取不了分层
 def load_psd(image):
@@ -344,7 +439,8 @@ def get_average_color_image(image):

    im = Image.new("RGB", (image.width, image.height), (average_red, average_green, average_blue))

-    return im
+    hex=rgb_to_hex((average_red, average_green, average_blue))
+    return (im,hex)



@@ -516,7 +612,7 @@ def merge_images(bg_image, layer_image, mask, x, y, width, height, scale_option)
    return bg_image


-
+# TODO 几个像素点的底
 def resize_image(layer_image, scale_option, width, height,color="white"):
    layer_image = layer_image.convert("RGB")
    original_width, original_height = layer_image.size
@@ -540,11 +636,11 @@ def resize_image(layer_image, scale_option, width, height,color="white"):
    elif scale_option == "center":
        # Scale image to minimum of width and height, center it, and fill extra area with black
        scale = min(width / original_width, height / original_height)
-        new_width = int(original_width * scale)
-        new_height = int(original_height * scale)
+        new_width = math.ceil(original_width * scale)
+        new_height = math.ceil(original_height * scale)
        resized_image = Image.new("RGB", (width, height), color=color)
        resized_image.paste(layer_image.resize((new_width, new_height)), ((width - new_width) // 2, (height - new_height) // 2))
-        resized_image=resized_image.convert("RGB")
+        resized_image = resized_image.convert("RGB")
        return resized_image
    
    return layer_image
@@ -552,6 +648,8 @@ def resize_image(layer_image, scale_option, width, height,color="white"):



+
+
 # def generate_text_image(text_list, font_path, font_size, text_color, vertical=True, spacing=0):
 #     # Load Chinese font
 #     font = ImageFont.truetype(font_path, font_size)
@@ -724,7 +822,7 @@ class SmoothMask:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/mask"
+    CATEGORY = "♾️Mixlab/Mask"

    INPUT_IS_LIST = False

@@ -749,79 +847,6 @@ class SmoothMask:



-class FeatheredMask:
-    @classmethod
-    def INPUT_TYPES(s):
-        return {
-                "required": {
-                                "mask": ("MASK",),
-                                "start_offset":("INT", {"default": 1, 
-                                                        "min": -150, 
-                                                        "max": 150, 
-                                                        "step": 1,
-                                                        "display": "slider"}),
-                                "feathering_weight":("FLOAT", {"default": 0.1,
-                                                                "min": 0.0,
-                                                                "max": 1,
-                                                                "step": 0.1,
-                                                                "display": "slider"})
-                            }
-            }
-    
-    RETURN_TYPES = ('MASK',)
-
-    FUNCTION = "run"
-
-    CATEGORY = "♾️Mixlab/mask"
-
-    OUTPUT_IS_LIST = (False,)
-  
-    # 运行的函数
-    def run(self,mask,start_offset, feathering_weight):
-        # print(mask.shape,mask.size())
-        
-        image=tensor2pil(mask)
-
-        # Open the image using PIL
-        image = image.convert("L")
-        if start_offset>0:
-            image=ImageOps.invert(image)
-
-        # Convert the image to a numpy array
-        image_np = np.array(image)
-
-        # Use Canny edge detection to get black contours
-        edges = cv2.Canny(image_np, 30, 150)
-
-        for i in range(0,abs(start_offset)):
-            # int(100*feathering_weight)
-            a=int(abs(start_offset)*0.1*i)
-            # Dilate the black contours to make them wider
-            kernel = np.ones((a, a), np.uint8)
-
-            dilated_edges = cv2.dilate(edges, kernel, iterations=1)
-            # dilated_edges = cv2.erode(edges, kernel, iterations=1)
-            # Smooth the dilated edges using Gaussian blur
-            smoothed_edges = cv2.GaussianBlur(dilated_edges, (5, 5), 0)
-
-            # Adjust the feathering weight
-            feathering_weight = max(0, min(feathering_weight, 1))
-
-            # Blend the smoothed edges with the original image to achieve feathering effect
-            image_np = cv2.addWeighted(image_np, 1, smoothed_edges, feathering_weight, feathering_weight)
-
-        # Convert the result back to PIL image
-        result_image = Image.fromarray(np.uint8(image_np))
-        result_image=result_image.convert("L")
-
-        if start_offset>0:
-            result_image=ImageOps.invert(result_image)
-        
-        mask=pil2tensor(result_image)
-        # print(mask.shape,mask.size())
-        return mask
-
-


 class SplitLongMask:
@@ -839,7 +864,7 @@ class SplitLongMask:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/mask"
+    CATEGORY = "♾️Mixlab/Mask"

    OUTPUT_IS_LIST = (True,)
  
@@ -883,7 +908,7 @@ class TransparentImage:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    # INPUT_IS_LIST = True， 一个batch传进来
    OUTPUT_IS_LIST = (True,True,True,)
@@ -891,7 +916,7 @@ class TransparentImage:

    # 运行的函数
    def run(self,images,masks,invert,save,filename_prefix,prompt=None, extra_pnginfo=None):
-        print('TransparentImage',images.shape,images.size())
+        # print('TransparentImage',images.shape,images.size(),masks.shape,masks.size())
        # print(masks.shape,masks.size())

        ui_images=[]
@@ -901,11 +926,16 @@ class TransparentImage:
        masks_new=[]
        nh=masks.shape[0]//count

-        #INPUT_IS_LIST = False, 一个batch传进来
-        if nh*count==masks.shape[0]:
-            masks_new=split_mask_by_new_height(masks,nh)
+        masks_new=masks
+
+        if images.shape[0]==masks.shape[0] and  images.shape[1]==masks.shape[1] and  images.shape[2]==masks.shape[2]:
+            print('TransparentImage',images.shape,images.size(),masks.shape,masks.size())
        else:
-            masks_new=split_mask_by_new_height(masks,masks.shape[0])
+            #INPUT_IS_LIST = False, 一个batch传进来
+            if nh*count==masks.shape[0]:
+                masks_new=split_mask_by_new_height(masks,nh)
+            else:
+                masks_new=split_mask_by_new_height(masks,masks.shape[0])


        is_save=True if save=='yes' else False
@@ -955,7 +985,7 @@ class EnhanceImage:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = True

@@ -1021,7 +1051,7 @@ class LoadImagesFromPath:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    # INPUT_IS_LIST = True
    OUTPUT_IS_LIST = (True,True,False,)
@@ -1047,7 +1077,7 @@ class LoadImagesFromPath:
            if watcher_folder!=None:
                watcher_folder.stop()

-
+        #TODO 修bug： ps6477. tmp 
        images=get_images_filepath(file_path,white_bg=='enable')

        # 当开启了监听，则取最新的，第一个文件
@@ -1075,7 +1105,7 @@ class LoadImagesFromPath:
            print("发生了一个未知的错误：", str(e))

        # print('#prompt::::',prompt)
-        return (imgs,masks,prompt,)
+        return  {"ui": {"seed": [1]}, "result":(imgs,masks,prompt,)}


 # TODO 扩大选区的功能,重新输出mask
@@ -1086,29 +1116,81 @@ class ImageCropByAlpha:
                             "RGBA": ("RGBA",),  },
                }
    
-    RETURN_TYPES = ("IMAGE",)
-    # RETURN_NAMES = ("WIDTH","HEIGHT","X","Y",)
+    RETURN_TYPES = ("IMAGE","MASK","MASK","INT","INT","INT","INT",)
+    RETURN_NAMES = ("IMAGE","MASK","AREA_MASK","x","y","width","height",)

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

-    INPUT_IS_LIST = False
-    OUTPUT_IS_LIST = (False,)
+    INPUT_IS_LIST = True
+    OUTPUT_IS_LIST = (True,True,True,True,True,True,True,)

    def run(self,image,RGBA):
+        # print(image.shape,RGBA.shape)
+
+        image=image[0]
+        RGBA=RGBA[0]
+
+        bf_im = tensor2pil(image)
+
        # print(RGBA)
        im=tensor2pil(RGBA)
        im=naive_cutout(im,im)
        x, y, w, h=get_not_transparent_area(im)
-        print('#ForImageCrop:',w, h,x, y,)
+        # print('#ForImageCrop:',w, h,x, y,)

        x = min(x, image.shape[2] - 1)
        y = min(y, image.shape[1] - 1)
        to_x = w + x
        to_y = h + y
+
+        x_1=x
+        y_1=y
+        width_1=w
+        height_1=h
+
        img = image[:,y:to_y, x:to_x, :]
-        return (img,)
+
+
+        # 原图的mask
+        ori=RGBA[:,y:to_y, x:to_x, :]
+        ori=tensor2pil(ori)
+
+        # 创建一个新的图像对象，大小和模式与原始图像相同
+        new_image = Image.new("RGBA", ori.size)
+
+        # 获取原始图像的像素数据
+        pixel_data = ori.load()
+
+        # 获取新图像的像素数据
+        new_pixel_data = new_image.load()
+
+        # 遍历图像的每个像素
+        for y in range(ori.size[1]):
+            for x in range(ori.size[0]):
+                # 获取当前像素的RGBA值
+                r, g, b, a = pixel_data[x, y]
+
+                # 如果a通道不为0（不透明），将当前像素设置为白色
+                if a != 0:
+                    new_pixel_data[x, y] = (255, 255, 255, 255)
+                else:
+                    new_pixel_data[x, y] = (r, g, b, a)
+
+        # 保存修改后的图像
+        # new_image.save("output.png")
+                    
+        ori=new_image.convert('L')
+        # threshold = 128
+        # ori = ori.point(lambda x: 0 if x < threshold else 255, '1')
+        ori=pil2tensor(ori)
+
+        # 矩形区域，mask
+        b_image =AreaToMask_run(RGBA)
+        # img=None
+        # b_image=None
+        return ([img],[ori],[b_image],[x_1],[y_1],[width_1],[height_1],)



@@ -1146,7 +1228,7 @@ class TextImage:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,False,)
@@ -1175,7 +1257,7 @@ class LoadImagesFromURL:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (True,True,)
@@ -1232,7 +1314,7 @@ class SvgImage:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,True,)
@@ -1266,7 +1348,7 @@ class Image3D:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,False,False,False,)
@@ -1306,6 +1388,24 @@ class Image3D:



+def AreaToMask_run(RGBA):
+    # print(RGBA)
+    im=tensor2pil(RGBA)
+    im=naive_cutout(im,im)
+    x, y, w, h=get_not_transparent_area(im)
+        
+    im=im.convert("RGBA")
+        # print('#AreaToMask:',im)
+    img=areaToMask(x,y,w,h,im)
+    img=img.convert("RGBA")
+    mask=pil2tensor(img)
+
+    channels = ["red", "green", "blue", "alpha"]
+    # print(mask,mask.shape)
+    mask = mask[:, :, :, channels.index("green")]
+
+    return mask
+

 class AreaToMask:
    @classmethod
@@ -1318,26 +1418,14 @@ class AreaToMask:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/mask"
+    CATEGORY = "♾️Mixlab/Mask"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)

    def run(self,RGBA):
-        # print(RGBA)
-        im=tensor2pil(RGBA)
-        im=naive_cutout(im,im)
-        x, y, w, h=get_not_transparent_area(im)
-        
-        im=im.convert("RGBA")
-        # print('#AreaToMask:',im)
-        img=areaToMask(x,y,w,h,im)
-        img=img.convert("RGBA")
-        mask=pil2tensor(img)

-        channels = ["red", "green", "blue", "alpha"]
-        # print(mask,mask.shape)
-        mask = mask[:, :, :, channels.index("green")]
+        mask =AreaToMask_run(RGBA)

        return (mask,)

@@ -1353,7 +1441,7 @@ class FaceToMask:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/mask"
+    CATEGORY = "♾️Mixlab/Mask"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -1398,7 +1486,7 @@ class EmptyLayer:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/layer"
+    CATEGORY = "♾️Mixlab/Layer"

    OUTPUT_IS_LIST = (True,)

@@ -1479,7 +1567,7 @@ class NewLayer:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/layer"
+    CATEGORY = "♾️Mixlab/Layer"

    INPUT_IS_LIST = True
    OUTPUT_IS_LIST = (True,)
@@ -1510,6 +1598,112 @@ class NewLayer:

        return (layer_n,)

+
+def splitImage(image, num):
+    width, height = image.size
+
+    num_rows = int(num ** 0.5)
+    num_cols = int(num / num_rows)
+    
+    grid_width = width // num_cols
+    grid_height = height // num_rows
+
+    grid_coordinates = []
+    for i in range(num_rows):
+        for j in range(num_cols):
+            x = j * grid_width
+            y = i * grid_height
+            grid_coordinates.append((x, y, grid_width, grid_height))
+
+    return grid_coordinates
+
+# # 读取图片
+# image = Image.open("path_to_your_image.jpg")
+
+# # 定义要切割的区域数量
+# num = 9
+
+# # 切割图片
+# grid_coordinates = splitImage(image, num)
+
+# # 输出切割区域坐标
+# for i, coordinates in enumerate(grid_coordinates):
+#     print(f"Region {i + 1}: x={coordinates[0]}, y={coordinates[1]}, width={coordinates[2]}, height={coordinates[3]}")
+
+
+class SplitImage:
+    @classmethod
+    def INPUT_TYPES(s):
+        return { 
+            "required": { 
+                "image": ("IMAGE",), 
+                "num": ("INT",{
+                    "default": 4, 
+                    "min": 1, #Minimum value
+                    "max": 500, #Maximum value
+                    "step": 1, #Slider's step
+                    "display": "number" # Cosmetic only: display as "number" or "slider"
+                }),
+                "seed": ("INT",{
+                    "default": 4, 
+                    "min": 1, #Minimum value
+                    "max": 500, #Maximum value
+                    "step": 1, #Slider's step
+                    "display": "number" # Cosmetic only: display as "number" or "slider"
+                }),
+            }
+                }
+    
+    RETURN_TYPES = ("_GRID","_GRID",)
+    RETURN_NAMES = ("grids","grid")
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Layer"
+
+    INPUT_IS_LIST = False
+    # OUTPUT_IS_LIST = (True,)
+
+    def run(self,image,num,seed):
+        image=tensor2pil(image)
+
+        grids=splitImage(image,num)
+
+        if seed>=num:
+            num=int(seed / 500 * num)-1
+        else:
+            num=seed-1
+
+        num=max(0,num) 
+
+        g=grids[num]
+
+        return (grids,g,)
+
+
+class GridOutput:
+    @classmethod
+    def INPUT_TYPES(s):
+        return { 
+            "required": {
+                "grid": ("_GRID",)
+            }
+                }
+    
+    RETURN_TYPES = ("INT","INT","INT","INT",)
+    RETURN_NAMES = ("x","y","width","height",)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Layer"
+
+    INPUT_IS_LIST = False
+    # OUTPUT_IS_LIST = (True,)
+
+    def run(self,grid):
+        x,y,w,h=grid
+        return (x,y,w,h,)
+
 class ShowLayer:
    @classmethod
    def INPUT_TYPES(s):
@@ -1567,7 +1761,7 @@ class ShowLayer:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/layer"
+    CATEGORY = "♾️Mixlab/Layer"

    INPUT_IS_LIST = True
    # OUTPUT_IS_LIST = (True,)
@@ -1606,12 +1800,12 @@ class MergeLayers:

                }
    
-    RETURN_TYPES = ("IMAGE",)
-    # RETURN_NAMES = ("WIDTH","HEIGHT","X","Y",)
+    RETURN_TYPES = ("IMAGE","MASK",)
+    RETURN_NAMES = ("IMAGE","MASK",)

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/layer"
+    CATEGORY = "♾️Mixlab/Layer"

    INPUT_IS_LIST = True
    # OUTPUT_IS_LIST = (False,)
@@ -1632,7 +1826,10 @@ class MergeLayers:
                bg_image=tensor2pil(bg_image)
                # 按z-index排序
                layers_new = sorted(layers, key=lambda x: x["z_index"])
-            
+                
+                width, height = bg_image.size
+                final_mask= Image.new('L', (width, height), 0)
+
                for layer in layers_new:
                    image=layer['image']
                    mask=layer['mask']
@@ -1658,25 +1855,32 @@ class MergeLayers:
                                        layer['scale_option']
                                        )
                    
-                mask=bg_image.convert('RGBA')
-                mask=pil2tensor(mask)
+                    final_mask=merge_images(final_mask,
+                                        layer_mask.convert('RGB'),
+                                        layer_mask,
+                                        layer['x'],
+                                        layer['y'],
+                                        layer['width'],
+                                        layer['height'],
+                                        layer['scale_option']
+                                        )
+                    
+                    final_mask=final_mask.convert('L')
+                    
+                # mask=bg_image.convert('RGBA')
+                final_mask=pil2tensor(final_mask)
                
                bg_image=bg_image.convert('RGB')
                bg_image=pil2tensor(bg_image)

-                channels = ["red", "green", "blue", "alpha"]
-                # print(mask,mask.shape)
-                mask = mask[:, :, :, channels.index("green")]
-
                bg_images.append(bg_image)
-                masks.append(mask)
+                masks.append(final_mask)
        
        bg_images=torch.cat(bg_images, dim=0)
        masks=torch.cat(masks, dim=0)
        return (bg_images,masks,)
    

-
 class GradientImage:
    @classmethod
    def INPUT_TYPES(s):
@@ -1707,7 +1911,7 @@ class GradientImage:
    FUNCTION = "run"

    # 右键菜单目录
-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    # 输入是否为列表
    INPUT_IS_LIST = False
@@ -1787,7 +1991,7 @@ class NoiseImage:
    FUNCTION = "run"

    # 右键菜单目录
-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    # 输入是否为列表
    INPUT_IS_LIST = False
@@ -1857,15 +2061,15 @@ class ResizeImage:
            }
                }
    
-    RETURN_TYPES = ("IMAGE","IMAGE")
-    RETURN_NAMES = ("image","average_image",)
+    RETURN_TYPES = ("IMAGE","IMAGE","STRING",)
+    RETURN_NAMES = ("image","average_image","average_hex",)

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = True
-    OUTPUT_IS_LIST = (True,True,)
+    OUTPUT_IS_LIST = (True,True,True,)

    def run(self,width,height,scale_option,image=None,average_color=['on'],fill_color=["#FFFFFF"]):
        
@@ -1877,28 +2081,134 @@ class ResizeImage:

        imgs=[]
        average_images=[]
+        hexs=[]

        if image==None:
            im=create_noisy_image(w,h,"RGB")
-            a_im=get_average_color_image(im)
+            a_im,hex=get_average_color_image(im)
            
            im=pil2tensor(im)
            imgs.append(im)

            a_im=pil2tensor(a_im)
            average_images.append(a_im)
+            hexs.append(hex)
        else:
-            for im in image:
-                im=tensor2pil(im)
-                im=resize_image(im,scale_option,w,h,fill_color)
-                im=im.convert('RGB')
+            for ims in image:
+                for im in ims:
+                    im=tensor2pil(im)
+                    im=resize_image(im,scale_option,w,h,fill_color)
+                    im=im.convert('RGB')

-                a_im=get_average_color_image(im)
+                    a_im,hex=get_average_color_image(im)

-                im=pil2tensor(im)
-                imgs.append(im)
+                    im=pil2tensor(im)
+                    imgs.append(im)

-                a_im=pil2tensor(a_im)
-                average_images.append(a_im)
+                    a_im=pil2tensor(a_im)
+                    average_images.append(a_im)
+                    hexs.append(hex)
        
-        return (imgs,average_images,)
+        return (imgs,average_images,hexs,)
+
+
+class MirroredImage:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                "image": ("IMAGE",),
+                },
+                }
+    
+    # 输出的数据类型
+    RETURN_TYPES = ("IMAGE",)
+
+    # 运行时方法名称
+    FUNCTION = "run"
+
+    # 右键菜单目录
+    CATEGORY = "♾️Mixlab/Image"
+
+    # 输入是否为列表
+    INPUT_IS_LIST = True
+
+    # 输出是否为列表
+    OUTPUT_IS_LIST = (True,)
+
+    def run(self,image):
+        res=[]
+        for ims in image:
+            for im in ims:
+                img=tensor2pil(im)
+                mirrored_image = img.transpose(Image.FLIP_LEFT_RIGHT)
+                img=pil2tensor(mirrored_image)
+                res.append(img)
+        return (res,)
+
+
+
+class GetImageSize_:
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "image": ("IMAGE",),
+            }
+        }
+
+    RETURN_TYPES = ("INT", "INT")
+    RETURN_NAMES = ("width", "height")
+
+    FUNCTION = "get_size"
+
+    CATEGORY = "♾️Mixlab/Image"
+
+    def get_size(self, image):
+        _, height, width, _ = image.shape
+        return (width, height)
+
+
+
+class ImageColorTransfer:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                "source": ("IMAGE",),
+                "target": ("IMAGE",),
+                },
+                }
+    
+    # 输出的数据类型
+    RETURN_TYPES = ("IMAGE",)
+
+    # 运行时方法名称
+    FUNCTION = "run"
+
+    # 右键菜单目录
+    CATEGORY = "♾️Mixlab/Image"
+
+    # 输入是否为列表
+    INPUT_IS_LIST = True
+
+    # 输出是否为列表
+    OUTPUT_IS_LIST = (True,)
+
+    def run(self,source,target):
+
+        res=[]
+
+        target=target[0][0]
+        print(target.shape)
+        target=tensor2pil(target)
+
+        for ims in source:
+            for im in ims:
+                image=tensor2pil(im)
+                image=color_transfer(image,target)
+                image=pil2tensor(image)
+                res.append(image)
+
+        return (res,)
+
+
+
@@ -1,12 +1,46 @@
-import os
+import os,sys
 import folder_paths
-from simple_lama_inpainting import SimpleLama
-from PIL import Image

+from PIL import Image
+import importlib.util
 import numpy as np

 import torch

+global _available
+_available=False
+
+def is_installed(package):
+    try:
+        spec = importlib.util.find_spec(package)
+    except ModuleNotFoundError:
+        return False
+    return spec is not None
+
+if is_installed('simple_lama_inpainting')==False:
+    import subprocess
+    from packaging import version
+    
+    if version.parse(torch.__version__)>=version.parse('2.1'):
+        # 安装
+        print('#pip install simple_lama_inpainting')
+
+        result = subprocess.run([sys.executable, '-s', '-m', 'pip', 'install', 'simple_lama_inpainting'], capture_output=True, text=True)
+
+        #检查命令执行结果
+        if result.returncode == 0:
+            print("#install success")
+            from simple_lama_inpainting import SimpleLama
+            _available=True
+        else:
+            print("#install error")
+    else:
+        print('#pls check your torch version >= 2.1')
+
+else:
+    from simple_lama_inpainting import SimpleLama
+    _available=True
+

 
 llma_model_path=os.path.join(folder_paths.models_dir, "lama/big-lama.pt")
@@ -38,6 +72,8 @@ def pil2tensor(image):


 class LaMaInpainting:
+    global _available
+    available=_available
    @classmethod
    def INPUT_TYPES(s):
        return {"required": {
@@ -52,7 +88,7 @@ class LaMaInpainting:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    INPUT_IS_LIST = True
    OUTPUT_IS_LIST = (True,)
@@ -0,0 +1,171 @@
+ 
+import scipy.ndimage
+import torch
+
+from nodes import MAX_RESOLUTION
+
+import numpy as np 
+# from PIL import Image, ImageDraw
+from PIL import Image, ImageOps 
+
+from comfy.cli_args import args
+import cv2
+
+
+
+# Tensor to PIL
+def tensor2pil(image):
+    return Image.fromarray(np.clip(255. * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8))
+
+# Convert PIL to Tensor
+def pil2tensor(image):
+    return torch.from_numpy(np.array(image).astype(np.float32) / 255.0).unsqueeze(0)
+
+
+def grow(mask, expand, tapered_corners):
+    c = 0 if tapered_corners else 1
+    kernel = np.array([[c, 1, c],
+                            [1, 1, 1],
+                            [c, 1, c]])
+    mask = mask.reshape((-1, mask.shape[-2], mask.shape[-1]))
+    out = []
+    for m in mask:
+        output = m.numpy()
+        for _ in range(abs(expand)):
+            if expand < 0:
+                output = scipy.ndimage.grey_erosion(output, footprint=kernel)
+            else:
+                output = scipy.ndimage.grey_dilation(output, footprint=kernel)
+        output = torch.from_numpy(output)
+        out.append(output)
+    return torch.stack(out, dim=0)
+
+def combine(destination, source, x, y):
+    output = destination.reshape((-1, destination.shape[-2], destination.shape[-1])).clone()
+    source = source.reshape((-1, source.shape[-2], source.shape[-1]))
+
+    left, top = (x, y,)
+    right, bottom = (min(left + source.shape[-1], destination.shape[-1]), min(top + source.shape[-2], destination.shape[-2]))
+    visible_width, visible_height = (right - left, bottom - top,)
+
+    source_portion = source[:, :visible_height, :visible_width]
+    destination_portion = destination[:, top:bottom, left:right]
+ 
+    #operation == "subtract":
+    output[:, top:bottom, left:right] = destination_portion - source_portion
+        
+    output = torch.clamp(output, 0.0, 1.0)
+
+    return output
+
+class OutlineMask:
+
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+                "required": {
+                                "mask": ("MASK",),
+                                "outline_width":("INT", {"default": 10,"min": 1, "max": MAX_RESOLUTION, "step": 1}),
+                                "tapered_corners": ("BOOLEAN", {"default": True}),
+                            }
+            }
+    
+    RETURN_TYPES = ('MASK',)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Mask"
+
+    # 运行的函数
+    def run(self, mask, outline_width, tapered_corners):
+
+        m1=grow(mask,outline_width,tapered_corners)
+        m2=grow(mask,-outline_width,tapered_corners)
+
+        m3=combine(m1,m2,0,0)
+
+        return (m3,)
+    
+
+
+
+class FeatheredMask:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+                "required": {
+                                "mask": ("MASK",),
+                                "start_offset":("INT", {"default": 1, 
+                                                        "min": -150, 
+                                                        "max": 150, 
+                                                        "step": 1,
+                                                        "display": "slider"}),
+                                "feathering_weight":("FLOAT", {"default": 0.1,
+                                                                "min": 0.0,
+                                                                "max": 1,
+                                                                "step": 0.1,
+                                                                "display": "slider"})
+                            }
+            }
+    
+    RETURN_TYPES = ('MASK',)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Mask"
+
+    OUTPUT_IS_LIST = (True,)
+  
+    # 运行的函数
+    def run(self,mask,start_offset, feathering_weight):
+        # print(mask.shape,mask.size())
+        
+        num,_,_=mask.size()
+
+        masks=[]
+
+        for i in range(num):
+            mm=mask[i]
+            image=tensor2pil(mm)
+
+            # Open the image using PIL
+            image = image.convert("L")
+            if start_offset>0:
+                image=ImageOps.invert(image)
+
+            # Convert the image to a numpy array
+            image_np = np.array(image)
+
+            # Use Canny edge detection to get black contours
+            edges = cv2.Canny(image_np, 30, 150)
+
+            for i in range(0,abs(start_offset)):
+                # int(100*feathering_weight)
+                a=int(abs(start_offset)*0.1*i)
+                # Dilate the black contours to make them wider
+                kernel = np.ones((a, a), np.uint8)
+
+                dilated_edges = cv2.dilate(edges, kernel, iterations=1)
+                # dilated_edges = cv2.erode(edges, kernel, iterations=1)
+                # Smooth the dilated edges using Gaussian blur
+                smoothed_edges = cv2.GaussianBlur(dilated_edges, (5, 5), 0)
+
+                # Adjust the feathering weight
+                feathering_weight = max(0, min(feathering_weight, 1))
+
+                # Blend the smoothed edges with the original image to achieve feathering effect
+                image_np = cv2.addWeighted(image_np, 1, smoothed_edges, feathering_weight, feathering_weight)
+
+            # Convert the result back to PIL image
+            result_image = Image.fromarray(np.uint8(image_np))
+            result_image=result_image.convert("L")
+
+            if start_offset>0:
+                result_image=ImageOps.invert(result_image)
+            
+            result_image=result_image.convert("L")
+            mt=pil2tensor(result_image)
+            masks.append(mt)
+         
+            # print( mt.size())
+        return (masks,)
@@ -12,6 +12,30 @@ from PIL.PngImagePlugin import PngInfo
 #     req =  request.Request("http://127.0.0.1:8188/prompt", data=data)
 #     request.urlopen(req)    

+embeddings_path=os.path.join(folder_paths.models_dir, "embeddings")
+
+def get_files_with_extension(directory, extension):
+    file_list = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            if file.endswith(extension):
+                file_name = os.path.splitext(file)[0]
+                file_list.append(file_name)
+    return file_list
+
+def join_with_(text_list,delimiter):
+    joined_text = delimiter.join(text_list)
+    return joined_text
+
+
+class AnyType(str):
+  """A special class that is always equal in not equal comparisons. Credit to pythongosssss"""
+
+  def __ne__(self, __value: object) -> bool:
+    return False
+
+any_type = AnyType("*")
+

 default_prompt1='''Swing
                                                Slide
@@ -54,7 +78,7 @@ def addWeight(text, weight=1):
    if weight == 1:
        return text
    else:
-        return f"({text}:{round(weight,2)})"
+        return f"({text}:{round(weight,3)})"

 def prompt_delete_words(sentence, new_words_length):
    # 使用逗号分割句子，并去除空格
@@ -114,7 +138,7 @@ class PromptImage:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/prompt"
+    CATEGORY = "♾️Mixlab/Prompt"

    # 运行的函数
    def run(self,prompts,images,save_to_image):
@@ -193,7 +217,7 @@ class PromptSimplification:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/prompt"
+    CATEGORY = "♾️Mixlab/Prompt"

    INPUT_IS_LIST = True
    OUTPUT_IS_LIST = (True,)
@@ -254,7 +278,7 @@ class PromptSlide:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/prompt"
+    CATEGORY = "♾️Mixlab/Prompt"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -297,7 +321,9 @@ class RandomPrompt:
                            "default": 'sticker, Cartoon, ``'
                          }),
                "random_sample": (["enable", "disable"],),
-                }
+                # "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff, "step": 1}),
+                },
+           
            }
    
    
@@ -306,7 +332,7 @@ class RandomPrompt:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/prompt"
+    CATEGORY = "♾️Mixlab/Prompt"

    OUTPUT_IS_LIST = (True,)
    OUTPUT_NODE = True
@@ -334,7 +360,10 @@ class RandomPrompt:
            for w2 in words2:
                w2=w2.strip()
                if '``' not in w2:
-                    w2=w2+',``'
+                    if w2=="":
+                        w2='``'
+                    else:
+                        w2=w2+',``'
                if w1!='' and w2!='':
                    prompts.append(w2.replace('``', w1))
                pbar.update(1)
@@ -357,62 +386,64 @@ class RandomPrompt:



-# class RunWorkflow:
-#     @classmethod
-#     def INPUT_TYPES(s):
-#         return {
-#             "required": {
-#                 "workflow": ("STRING", {
-#                             "multiline": False, 
-#                             "default": ''
-#                           }),
-#                 "prompt": ("STRING", {
-#                             "multiline": False, 
-#                             "default": ''
-#                           }),
-#                  "image": ("IMAGE",),
-#                  "input_node": ("STRING", {
-#                             "multiline": False, 
-#                             "default": ''
-#                           }),
-#                  "output_node": ("STRING", {
-#                             "multiline": False, 
-#                             "default": ''
-#                           }),
-#                 },
+
+class EmbeddingPrompt:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "embedding":(get_files_with_extension(embeddings_path,'.pt'),),
+                "weight": ("FLOAT", {"default": 1, "min": -2, "max": 2,"step":0.01 ,"display": "slider"}),
+                },
                
-#             }
+            }
    
+    RETURN_TYPES = ("STRING",)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Prompt"
+
+    OUTPUT_IS_LIST = (False,)
+    # OUTPUT_NODE = True
+
+    # 运行的函数
+    def run(self,embedding,weight):
+        weight = round(weight, 3)
+        prompt='embedding:'+embedding
+        if weight!=1:
+            prompt='('+prompt+':'+str(weight)+')'
+        prompt=" "+prompt+' ' 
+        # return (new_prompt)
+        return (prompt,)
+
+RETURN_TYPES = (any_type,)
+
+class JoinWithDelimiter:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                    "text_list": (any_type,),
+                    "delimiter":(["newline","comma"],),
+                             },
+                }
    
+    RETURN_TYPES = ("STRING",) 

-#     RETURN_TYPES = ("IMAGE","STRING",)
+    FUNCTION = "run"

-#     FUNCTION = "run"
+    CATEGORY = "♾️Mixlab/Prompt"

-#     CATEGORY = "♾️Mixlab/workflow"
-
-#     OUTPUT_IS_LIST = (True,)
-#     OUTPUT_NODE = True
-
-
-#     # 运行的函数
-#     def run(self,workflow,prompt,image,input_node,output_node):
-#         print('#运行的函数',prompt,image,input_node,output_node)
-#         workflow=json.loads(workflow)
-#         input_node=input_node.split(".")
-#         workflow[input_node[0]][input_node[1]][input_node[2]]=prompt
-
-#         workflow_new={}
-#         # 遍历，seed设为随机
-#         for key, value in workflow.items():
-#             if 'inputs' in value:
-#                 if 'seed' in value['inputs']:
-#                     value['inputs']['seed']= random.randint(1, 18446744073709551614)
-#             workflow_new[key]=value
-
-#         queue_prompt(workflow_new)
-#         print('#运行的函数',workflow_new[input_node[0]])
-
-#         # return (new_prompt)
-#         return  {"ui":{"images": []},"result": ([image],['text'],)}
+    INPUT_IS_LIST = True # 当true的时候，输入时list，当false的时候，如果输入是list，则会自动包一层for循环调用
+    OUTPUT_IS_LIST = (False,)

+    def run(self,text_list,delimiter):
+        delimiter=delimiter[0]
+        if delimiter =='newline':
+            delimiter='\n'
+        elif delimiter=='comma':
+            delimiter=','
+        t=''
+        if isinstance(text_list, list):
+            t=join_with_(text_list,delimiter)
+        return (t,)
@@ -0,0 +1,164 @@
+import os,sys
+import folder_paths
+
+from PIL import Image
+import importlib.util
+
+import comfy.utils
+import numpy as np
+import torch
+
+
+U2NET_HOME=os.path.join(folder_paths.models_dir, "rembg")
+os.environ["U2NET_HOME"] = U2NET_HOME
+
+global _available
+_available=False
+
+def is_installed(package):
+    try:
+        spec = importlib.util.find_spec(package)
+    except ModuleNotFoundError:
+        return False
+    return spec is not None
+
+
+try:
+    if is_installed('rembg')==False:
+        import subprocess
+
+        # 安装
+        print('#pip install rembg[gpu]')
+
+        result = subprocess.run([sys.executable, '-s', '-m', 'pip', 'install', 'rembg[gpu]'], capture_output=True, text=True)
+
+        #检查命令执行结果
+        if result.returncode == 0:
+            print("#install success")
+            from rembg import new_session, remove
+            _available=True
+        else:
+            print("#install error")
+        
+    else:
+        from rembg import new_session, remove
+        _available=True
+
+except:
+    _available=False
+
+
+def run_bg(model_name= "unet",images=[]):
+    # model_name = "unet" # "isnet-general-use"
+    rembg_session = new_session(model_name)
+    masks=[]
+    rgba_images=[]
+    rgb_images=[]
+    # 进度条
+    pbar = comfy.utils.ProgressBar(len(images) )
+    for img in images:
+        # use the post_process_mask argument to post process the mask to get better results.
+        mask = remove(img, session=rembg_session,only_mask=True,post_process_mask=True)
+        # mask=mask.convert('L')
+        # masks.append(mask)
+        if model_name=="u2net_cloth_seg":
+            width, original_height = mask.size
+            num_slices = original_height // img.height
+            for i in range(num_slices):
+                top = i * img.height
+                bottom = (i + 1) * img.height
+                slice_image = mask.crop((0, top, width, bottom))
+                slice_mask=slice_image.convert('L')
+                masks.append(slice_mask)
+
+                # rgba图
+                image_rgba = img.convert("RGBA")
+                image_rgba.putalpha(slice_mask)
+                rgba_images.append(image_rgba)
+
+                #rgb
+                rgb_image = Image.new("RGB", image_rgba.size, (0, 0, 0))
+                rgb_image.paste(image_rgba, mask=image_rgba.split()[3])
+                rgb_images.append(rgb_image)
+
+        else:
+            mask=mask.convert('L')    
+            # mask.save(output_path)
+            masks.append(mask)
+
+            # rgba图
+            image_rgba = img.convert("RGBA")
+            image_rgba.putalpha(mask)
+            rgba_images.append(image_rgba)
+
+            #rgb
+            rgb_image = Image.new("RGB", image_rgba.size, (0, 0, 0))
+            rgb_image.paste(image_rgba, mask=image_rgba.split()[3])
+            rgb_images.append(rgb_image)
+            
+        pbar.update(1)
+    return (masks,rgba_images,rgb_images)
+
+
+# Tensor to PIL
+def tensor2pil(image):
+    return Image.fromarray(np.clip(255. * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8))
+
+# Convert PIL to Tensor
+def pil2tensor(image):
+    return torch.from_numpy(np.array(image).astype(np.float32) / 255.0).unsqueeze(0)
+
+
+class RembgNode_:
+
+    global _available
+    available=_available
+    
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "image": ("IMAGE",),
+            "model_name": (["u2net",
+                            "u2netp",
+                            "u2net_human_seg",
+                            "u2net_cloth_seg",
+                            "silueta",
+                            "isnet-general-use",
+                            "isnet-anime",
+                            # "sam"
+                            ],),
+            
+                             },
+                }
+    
+    RETURN_TYPES = ("MASK","IMAGE","RGBA",)
+    RETURN_NAMES = ("masks","images","RGBAs")
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Mask"
+    OUTPUT_NODE = True
+    INPUT_IS_LIST = True
+    OUTPUT_IS_LIST = (True,True,True,)
+  
+    def run(self,image,model_name):
+        # 兼容list输入和batch输入
+
+        model_name=model_name[0]
+
+        images=[]
+        
+        for ims in image:
+            for im in ims:
+                im=tensor2pil(im)
+                images.append(im)
+
+        masks,rgba_images,rgb_images=run_bg(model_name,images)
+
+        masks=[pil2tensor(m) for m in masks]
+
+        rgba_images=[pil2tensor(m) for m in rgba_images]
+
+        rgb_images=[pil2tensor(m) for m in rgb_images]
+
+        return (masks,rgb_images,rgba_images,)
@@ -93,7 +93,7 @@ class ScreenShareNode:
    RETURN_NAMES = ("IMAGE","PROMPT","FLOAT","INT")
    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    # INPUT_IS_LIST = True
    OUTPUT_IS_LIST = (False,False,False,False)
@@ -118,7 +118,7 @@ class FloatingVideo:
    OUTPUT_NODE = True
    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/image"
+    CATEGORY = "♾️Mixlab/Image"

    # INPUT_IS_LIST = True
    # OUTPUT_IS_LIST = (False,False,)
@@ -0,0 +1,307 @@
+from transformers import pipeline, set_seed,AutoTokenizer, AutoModelForSeq2SeqLM
+import random
+import re
+
+import os,sys
+import folder_paths
+
+# from PIL import Image
+import importlib.util
+
+import comfy.utils
+# import numpy as np
+import torch
+import random
+
+global _available
+_available=True
+
+
+text_generator_model_path=os.path.join(folder_paths.models_dir, "prompt_generator/text2image-prompt-generator")
+if not os.path.exists(text_generator_model_path):
+    print(f"## text_generator_model not found: {text_generator_model_path}, pls download from https://huggingface.co/succinctly/text2image-prompt-generator/tree/main")
+    text_generator_model_path='succinctly/text2image-prompt-generator'
+
+zh_en_model_path=os.path.join(folder_paths.models_dir, "prompt_generator/opus-mt-zh-en")
+if not os.path.exists(zh_en_model_path):
+    print(f"## zh_en_model not found: {zh_en_model_path}, pls download from https://huggingface.co/Helsinki-NLP/opus-mt-zh-en/tree/main")
+    zh_en_model_path='Helsinki-NLP/opus-mt-zh-en'
+
+
+
+def is_installed(package):
+    try:
+        spec = importlib.util.find_spec(package)
+    except ModuleNotFoundError:
+        return False
+    return spec is not None
+
+
+try:
+    if is_installed('sentencepiece')==False:
+        import subprocess
+
+        # 安装
+        print('#pip install sentencepiece')
+
+        result = subprocess.run([sys.executable, '-s', '-m', 'pip', 'install', 'sentencepiece'], capture_output=True, text=True)
+
+        #检查命令执行结果
+        if result.returncode == 0 and is_installed('sentencepiece'):
+            print("#install success")
+            _available=True
+        else:
+            print("#install error")
+            _available=False
+        
+    else:
+        _available=True
+
+except:
+    _available=False
+
+
+
+def translate(zh_en_tokenizer,zh_en_model,text):
+    with torch.no_grad():
+        encoded = zh_en_tokenizer([text], return_tensors="pt")
+        encoded.to(zh_en_model.device)
+        sequences = zh_en_model.generate(**encoded)
+        return zh_en_tokenizer.batch_decode(sequences, skip_special_tokens=True)[0]
+
+# input = "青春不能回头，所以青春没有终点。 ——《火影忍者》"
+# print(input, translate(input))
+
+
+def text_generate(text_pipe,input,seed=None):
+    
+    if seed==None:
+        seed = random.randint(100, 1000000)
+    
+    set_seed(seed)
+
+    for count in range(6):    
+        sequences = text_pipe(input, max_length=random.randint(60, 90), num_return_sequences=8)
+        list = []
+        for sequence in sequences:
+            line = sequence['generated_text'].strip()
+            if line != input and len(line) > (len(input) + 4) and line.endswith((":", "-", "—")) is False:
+                list.append(line)
+
+        result = "\n".join(list)
+        result = re.sub('[^ ]+\.[^ ]+','', result)
+        result = result.replace("<", "").replace(">", "")
+        if result != "":
+            return result
+        if count == 5:
+            return result
+
+# input = "Youth can't turn back, so there's no end to youth."
+# print(input, text_generate(input))
+
+    
+import re
+
+def correct_prompt_syntax(prompt):
+
+    print("input prompt",prompt)
+    corrected_elements = []
+    # 处理成统一的英文标点
+    prompt = prompt.replace('（', '(').replace('）', ')').replace('，', ',').replace(';', ',').replace('。', '.').replace('：',':')
+    # 删除多余的空格
+    prompt = re.sub(r'\s+', ' ', prompt).strip()
+
+    # 分词
+    prompt_elements = prompt.split(',')
+
+    for element in prompt_elements:
+        element = element.strip()
+
+        # 处理空元素
+        if not element:
+            continue
+
+        # 检查并处理圆括号、方括号、尖括号
+        if element[0] in '([':
+            corrected_element = balance_brackets(element, '(', ')') if element[0] == '(' else balance_brackets(element, '[', ']')
+        elif element[0] == '<':
+            corrected_element = balance_brackets(element, '<', '>')
+        else:
+            # 删除开头的右括号或右方括号
+            corrected_element = element.lstrip(')]')
+
+        corrected_elements.append(corrected_element)
+
+    # 重组修正后的prompt
+    corrected_prompt = ', '.join(corrected_elements)
+    print("output prompt",corrected_prompt)
+    return corrected_prompt
+
+def balance_brackets(element, open_bracket, close_bracket):
+    open_brackets_count = element.count(open_bracket)
+    close_brackets_count = element.count(close_bracket)
+    return element + close_bracket * (open_brackets_count - close_brackets_count)
+
+# # 示例使用
+# test_prompt = "((middle-century castles)), [forsaken: 0.8], (mystery dragons: 1.3, mist forests, sunsets, quiet; (((dummy)), [fisting city: 0.5] background, radiant, soft and flavoured,] promising mountains, ((starry: 1.6), [[crowds], [middle-century castle: urban landscapes of the future: 0.5], [yellow: bright sun: 0.7], overlooking"
+# corrected_prompt = correct_prompt_syntax(test_prompt)
+# print(corrected_prompt)
+
+        
+        
+class ChinesePrompt:
+
+    global _available
+    available=_available
+    
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+               "text": ("STRING",{"multiline": True,"default": "", "dynamicPrompts": False}),
+               "generation": (["on","off"],{"default": "off"}), 
+                             },
+               
+                "optional":{
+                    "seed":("INT", {"default": 100, "min": 100, "max": 1000000}), 
+                    
+                },
+
+                }
+    
+    RETURN_TYPES = ("STRING",)
+    RETURN_NAMES = ("prompt",)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Prompt"
+    OUTPUT_NODE = True
+    INPUT_IS_LIST = True
+    OUTPUT_IS_LIST = (True,)
+
+    global text_pipe,zh_en_model,zh_en_tokenizer
+
+    text_pipe= None
+    zh_en_model=None
+    zh_en_tokenizer=None 
+
+    def run(self,text,seed,generation):
+        global text_pipe,zh_en_model,zh_en_tokenizer
+
+        seed=seed[0]
+        generation=generation[0]
+
+        # 进度条
+        pbar = comfy.utils.ProgressBar(len(text)+1)
+        
+        texts = [correct_prompt_syntax(t) for t in text]
+        print('correct_prompt_syntax::',texts)
+        if zh_en_model==None:
+            zh_en_model = AutoModelForSeq2SeqLM.from_pretrained(zh_en_model_path).eval()
+            zh_en_tokenizer = AutoTokenizer.from_pretrained(zh_en_model_path,padding=True, truncation=True)
+        
+        zh_en_model.to("cuda" if torch.cuda.is_available() else "cpu")
+            # zh_en_tokenizer.to("cuda" if torch.cuda.is_available() else "cpu")
+        
+        text_pipe=pipeline('text-generation', model=text_generator_model_path,device="cuda" if torch.cuda.is_available() else "cpu")
+        
+        # text_pipe.model.to("cuda" if torch.cuda.is_available() else "cpu")
+
+        prompt_result=[]
+
+        # print('zh_en_model device',zh_en_model.device,text_pipe.model.device,torch.cuda.current_device() )
+        en_texts=[]
+        for t in texts:
+            en_text=translate(zh_en_tokenizer,zh_en_model,t)
+            en_texts.append(en_text)
+
+        zh_en_model.to('cpu')
+        print("test en_text",en_texts)
+        # en_text.to("cuda" if torch.cuda.is_available() else "cpu")
+
+        pbar.update(1)
+        for t in en_texts:
+            if generation=='on':
+                prompt =text_generate(text_pipe,t,seed)
+                # 多条，还是单条
+                lines = prompt.split("\n")
+                longest_line = max(lines, key=len)
+                # print(longest_line)
+                prompt_result.append(longest_line)
+            else:
+                prompt_result.append(t)
+            pbar.update(1)
+
+        text_pipe.model.to('cpu')
+        prompt_result = [correct_prompt_syntax(p) for p in prompt_result]
+        
+        return {
+            "ui":{
+                    "prompt": prompt_result
+                },
+            "result": (prompt_result,)}
+
+
+class PromptGenerate:
+
+    global _available
+    available=_available
+    
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "text": ("STRING",{"multiline": True,"default": "", "dynamicPrompts": False}),
+                             },
+
+                "optional":{
+                    "multiple": (["off","on"],), 
+                    "seed":("INT", {"default": 100, "min": 100, "max": 1000000}), 
+                },
+
+                }
+    
+    RETURN_TYPES = ("STRING",)
+    RETURN_NAMES = ("prompt",)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/Prompt"
+    OUTPUT_NODE = True
+    INPUT_IS_LIST = True
+    OUTPUT_IS_LIST = (True,)
+
+    global text_pipe
+
+    text_pipe= None
+    # 
+
+    def run(self,text,multiple,seed):
+        global text_pipe
+
+        seed=seed[0]
+
+        multiple=multiple[0]
+
+        # 进度条
+        pbar = comfy.utils.ProgressBar(len(text))
+        
+        text_pipe=pipeline('text-generation', model=text_generator_model_path,device="cuda" if torch.cuda.is_available() else "cpu")
+        
+        prompt_result=[]
+
+        for t in text:
+            prompt =text_generate(text_pipe,t,seed)
+            prompt = prompt.split("\n")
+            if multiple=='off':
+                prompt = [max(prompt, key=len)]
+            
+            for p in prompt:
+                prompt_result.append(p)
+            pbar.update(1)
+
+        text_pipe.model.to('cpu')
+
+        return {
+            "ui":{
+                    "prompt": prompt_result
+                },
+            "result": (prompt_result,)}
@@ -1,10 +1,56 @@
-import os
-import re,random
+import os,platform
+import re,random,json
 from PIL import Image
 import numpy as np
 # FONT_PATH= os.path.abspath(os.path.join(os.path.dirname(__file__),'../assets/王汉宗颜楷体繁.ttf'))
 import folder_paths
 import matplotlib.font_manager as fm
+import torch
+
+def recursive_search(directory, excluded_dir_names=None):
+    if not os.path.isdir(directory):
+        return [], {}
+
+    if excluded_dir_names is None:
+        excluded_dir_names = []
+
+    result = []
+    dirs = {directory: os.path.getmtime(directory)}
+    for dirpath, subdirs, filenames in os.walk(directory, followlinks=True, topdown=True):
+        subdirs[:] = [d for d in subdirs if d not in excluded_dir_names]
+        for file_name in filenames:
+            relative_path = os.path.relpath(os.path.join(dirpath, file_name), directory)
+            result.append(relative_path)
+        for d in subdirs:
+            path = os.path.join(dirpath, d)
+            dirs[path] = os.path.getmtime(path)
+    return result, dirs
+
+def filter_files_extensions(files, extensions):
+    return sorted(list(filter(lambda a: os.path.splitext(a)[-1].lower() in extensions or len(extensions) == 0, files)))
+
+
+def get_system_font_path():
+    ps=[]
+    system = platform.system()
+    if system == "Windows":
+        ps.append(os.path.join(os.environ["WINDIR"], "Fonts"))
+    elif system == "Darwin":
+        ps.append(os.path.join("/Library", "Fonts"))
+    elif system == "Linux":
+        ps.append(os.path.join("/usr", "share", "fonts"))
+        ps.append(os.path.join("/usr", "local", "share", "fonts"))
+    ps=[p for p in ps if os.path.exists(p)]
+    file_paths=[]
+    for f in ps:
+        result, dirs=recursive_search(f)
+        for r in result:
+            file_paths.append(r)
+    file_paths=filter_files_extensions(file_paths,[".otf", ".ttf"])
+
+    return file_paths
+
+

 # import json
 # import hashlib
@@ -60,14 +106,14 @@ def get_font_files(directory):

    # 尝试获取系统字体
    try:
-        font_paths = fm.findSystemFonts()
-        for path in font_paths:
+        font_paths = get_system_font_path()
+        for file in font_paths:
            try:
-                font_prop = fm.FontProperties(fname=path)
-                font_name = font_prop.get_name()
-                font_files[font_name] = path
+                font_name = os.path.splitext(file)[0]
+                font_path = file
+                font_files[font_name] = os.path.abspath(font_path)
            except Exception as e:
-                print(f"Error processing font {path}: {e}")
+                print(f"Error processing font {file}: {e}")
    except Exception as e:
        print(f"Error finding system fonts: {e}")

@@ -85,7 +131,12 @@ def flatten_list(nested_list):
        if isinstance(item, list):
            flat_list.extend(flatten_list(item))
        else:
-            flat_list.append(item)
+            if torch.is_tensor(item):
+                print('item.shape',item.shape)
+                for i in range(item.shape[0]):
+                    flat_list.append(item[i:i + 1, ...])
+            else:
+                flat_list.append(item)
    return flat_list


@@ -103,7 +154,7 @@ class ColorInput:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,False,False,False,False,)
@@ -132,7 +183,7 @@ class FontInput:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -162,7 +213,7 @@ class TextToNumber:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -220,7 +271,7 @@ class FloatSlider:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -273,7 +324,7 @@ class IntNumber:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -290,11 +341,18 @@ class MultiplicationNode:
    def INPUT_TYPES(s):
        return {"required": {
                    "numberA":(any_type,),
-                    "numberB":("FLOAT", {
+                    "multiply_by":("FLOAT", {
                        "default": 0, 
-                        "min": -1, #Minimum value
+                        "min": -2, #Minimum value
                        "max": 0xffffffffffffffff,
-                        "step": 0.1, #Slider's step
+                        "step": 0.01, #Slider's step
+                        "display": "number" # Cosmetic only: display as "number" or "slider"
+                    }),
+                     "add_by":("FLOAT", {
+                        "default": 0, 
+                        "min": -2000, #Minimum value
+                        "max": 0xffffffffffffffff,
+                        "step": 0.01, #Slider's step
                        "display": "number" # Cosmetic only: display as "number" or "slider"
                    })
                             },
@@ -304,14 +362,14 @@ class MultiplicationNode:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,False,)

-    def run(self,numberA,numberB):
-        b=int(numberA*numberB)
-        a=float(numberA*numberB)
+    def run(self,numberA,multiply_by,add_by):
+        b=int(numberA*multiply_by+add_by)
+        a=float(numberA*multiply_by+add_by)
        return (a,b,) 

 class TextInput:
@@ -326,7 +384,7 @@ class TextInput:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -400,7 +458,7 @@ class DynamicDelayProcessor:
    RETURN_TYPES = (any_type,)
    RETURN_NAMES = ('output',)

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"
    def run(self,any_input,delay_seconds,delay_by_text,words_per_seconds,replace_output,replace_value):
        # print(f"Delay text:",delay_by_text )
        # 获取开始时间戳
@@ -434,12 +492,12 @@ class AppInfo:
    def INPUT_TYPES(s):
        return {"required": { 
                    "name": ("STRING",{"multiline": False,"default": "Mixlab-App","dynamicPrompts": False}),
-                    "image": ("IMAGE",),
                    "input_ids":("STRING",{"multiline": True,"default": "\n".join(["1","2","3"]),"dynamicPrompts": False}),
                    "output_ids":("STRING",{"multiline": True,"default": "\n".join(["5","9"]),"dynamicPrompts": False}),
                             },

                "optional":{
+                    "IMAGE": ("IMAGE",),
                    "description":("STRING",{"multiline": True,"default": "","dynamicPrompts": False}),
                    "version":("INT", {
                        "default": 1, 
@@ -451,12 +509,13 @@ class AppInfo:
                    "share_prefix":("STRING",{"multiline": False,"default": "","dynamicPrompts": False}),
                    "link":("STRING",{"multiline": False,"default": "https://","dynamicPrompts": False}),
                    "category":("STRING",{"multiline": False,"default": "","dynamicPrompts": False}),
+                    "auto_save": (["enable","disable"],),
                }

                }
    
-    RETURN_TYPES = ("IMAGE",)
-    RETURN_NAMES = ("IMAGE",)
+    RETURN_TYPES = ()
+    # RETURN_NAMES = ("IMAGE",)

    FUNCTION = "run"

@@ -464,11 +523,16 @@ class AppInfo:

    OUTPUT_NODE = True
    INPUT_IS_LIST = True
-    OUTPUT_IS_LIST = (True,)
+    # OUTPUT_IS_LIST = (True,)

-    def run(self,name,image,input_ids,output_ids,description,version,share_prefix,link,category):
+    def run(self,name,input_ids,output_ids,IMAGE,description,version,share_prefix,link,category,auto_save):
        name=name[0]
-        im=image[0][0]
+        
+        im=None
+        if IMAGE:
+            im=IMAGE[0][0]
+            #TODO batch 的方式需要处理
+            im=create_temp_file(im)
        # image [img,] img[batch,w,h,a] 列表里面是batch，

        input_ids=input_ids[0]
@@ -478,38 +542,14 @@ class AppInfo:
        share_prefix=share_prefix[0]
        link=link[0]
        category=category[0]
-
-        #TODO batch 的方式需要处理
-        im=create_temp_file(im)
        
        # id=get_json_hash([name,im,input_ids,output_ids,description,version])

-        return {"ui": {"json": [name,im,input_ids,output_ids,description,version,share_prefix,link,category]}, "result": (image,)}
+        return {"ui": {"json": [name,im,input_ids,output_ids,description,version,share_prefix,link,category]}, "result": ()}
    

    

-class GetImageSize_:
-    @classmethod
-    def INPUT_TYPES(cls):
-        return {
-            "required": {
-                "image": ("IMAGE",),
-            }
-        }
-
-    RETURN_TYPES = ("INT", "INT")
-    RETURN_NAMES = ("width", "height")
-
-    FUNCTION = "get_size"
-
-    CATEGORY = "♾️Mixlab/utils"
-
-    def get_size(self, image):
-        _, height, width, _ = image.shape
-        return (width, height)
-
-

 class SwitchByIndex:
    @classmethod
@@ -534,7 +574,7 @@ class SwitchByIndex:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = True
    OUTPUT_IS_LIST = (True,)
@@ -545,7 +585,8 @@ class SwitchByIndex:

        C=[]
        index=index[0]
-        for a in A:
+
+        for a in A:    
            C.append(a)
        for b in B:
            C.append(b)
@@ -558,6 +599,7 @@ class SwitchByIndex:
                C=[C[index]]
            except Exception as e:
                C=[]
+        
        return (C,)


@@ -590,7 +632,7 @@ class LimitNumber:

    FUNCTION = "run"

-    CATEGORY = "♾️Mixlab/utils"
+    CATEGORY = "♾️Mixlab/Utils"

    INPUT_IS_LIST = False
    OUTPUT_IS_LIST = (False,)
@@ -612,3 +654,61 @@ class LimitNumber:
        
        return (nn,)

+
+
+class ListStatistics:
+    @staticmethod
+    def count_types(lst):
+        type_count = {}
+
+        for item in lst:
+            item_type = type(item).__name__
+            if item_type not in type_count:
+                type_count[item_type] = []
+
+            if item_type in ['dict', 'str', 'int', 'float']:
+                type_count[item_type].append(item)
+
+        return type_count
+
+# # 示例列表
+# my_list = [1, 'hello', {'name': 'John'}, 3.14, {'age': 25}, 'world', 10]
+
+# # 创建ListStatistics对象
+# list_stats = ListStatistics()
+
+# # 调用count_types方法进行统计
+# result = list_stats.count_types(my_list)
+
+# # 输出结果
+# for item_type, values in result.items():
+#     print(item_type + ':')
+#     for value in values:
+#         print(value)
+#     print('---')
+
+class TESTNODE_:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "ANY":(any_type,), },
+                }
+    
+    RETURN_TYPES = (any_type,)
+
+    FUNCTION = "run"
+
+    CATEGORY = "♾️Mixlab/__TEST"
+
+    OUTPUT_NODE = True
+    INPUT_IS_LIST = True
+    OUTPUT_IS_LIST = (True,)
+
+    def run(self,ANY):
+        print(ANY)
+        # data=ANY
+        list_stats = ListStatistics()
+
+        # 调用count_types方法进行统计
+        result = list_stats.count_types(ANY)
+            
+        return {"ui": {"data": result,"type":[str(type(ANY[0]))]}, "result": (ANY,)}
@@ -145,7 +145,7 @@ class VAELoader:
    RETURN_TYPES = ("VAE",)
    FUNCTION = "load_vae"

-    CATEGORY = "♾️Mixlab/_test"
+    CATEGORY = "♾️Mixlab/__TEST"

    #TODO: scale factor?
    def load_vae(self, vae_name):
@@ -165,7 +165,7 @@ class VAEDecode:
    RETURN_TYPES = ("IMAGE",)
    FUNCTION = "decode"

-    CATEGORY = "♾️Mixlab/_test"
+    CATEGORY = "♾️Mixlab/__TEST"

    def decode(self, vae, samples):
        image = vae.decode(samples["samples"].to("cuda:0"))
@@ -303,10 +303,9 @@
        }


-
-        select,
-        button,
-        input {
+        .card select,
+        .card button,
+        .card input {
            height: 32px;
            cursor: pointer;
            background: #000000bf;
@@ -332,14 +331,53 @@
            font-size: 12px;
            width: 200px;
        }
+
+
+        /* 图像编辑器 */
+        #editor_container {
+            position: fixed;
+            top: 0;
+            z-index: 9;
+            background: #eee;
+            height: 100vh;
+            width: 100%;
+            display: none;
+        }
+
+
+        /* 图片的字幕 */
+        .pswp__custom-caption {
+            background: rgb(20 27 70);
+            font-size: 16px;
+            color: #fff;
+            width: calc(100% - 32px);
+            max-width: 400px;
+            padding: 2px 8px;
+            border-radius: 4px;
+            position: absolute;
+            left: 50%;
+            bottom: 16px;
+            transform: translateX(-50%);
+        }
+
+        .pswp__custom-caption a {
+            color: #fff;
+            text-decoration: underline;
+        }
+
+        .hidden-caption-content {
+            display: none;
+        }
    </style>
    <!-- <script src="../../../scripts/api.js" type="module"></script> -->
    <link href="/extensions/comfyui-mixlab-nodes/lib/photoswipe.min.css" rel="stylesheet">
    <link href="/extensions/comfyui-mixlab-nodes/lib/classic.min.css" rel="stylesheet">
    <script src="/extensions/comfyui-mixlab-nodes/lib/pickr.min.js"></script>
+    <script src="/extensions/comfyui-mixlab-nodes/lib/filerobot-image-editor.min.js"></script>
 </head>

 <body>
+    <div id="editor_container"></div>
    <div style="display: flex;
    align-items: center;
    justify-content: space-around;">
@@ -353,18 +391,18 @@
            <a class="link" href="https://www.mixcomfy.com" target="_blank">ComfyUI中文爱好者社区推荐</a>
        </div>

-        <a target="_blank" href="https://github.com/shadowcz007/comfyui-mixlab-nodes" style="text-decoration: none;
+        <a target="_blank" href="https://www.mixcomfy.com/blog/" style="text-decoration: none;
        color: black;font-size:12px">
            <svg height="32" aria-hidden="true" viewBox="0 0 16 16" version="1.1" width="32" data-view-component="true"
                class="octicon octicon-mark-github v-align-middle color-fg-default">
                <path
                    d="M8 0c4.42 0 8 3.58 8 8a8.013 8.013 0 0 1-5.45 7.59c-.4.08-.55-.17-.55-.38 0-.27.01-1.13.01-2.2 0-.75-.25-1.23-.54-1.48 1.78-.2 3.65-.88 3.65-3.95 0-.88-.31-1.59-.82-2.15.08-.2.36-1.02-.08-2.12 0 0-.67-.22-2.2.82-.64-.18-1.32-.27-2-.27-.68 0-1.36.09-2 .27-1.53-1.03-2.2-.82-2.2-.82-.44 1.1-.16 1.92-.08 2.12-.51.56-.82 1.28-.82 2.15 0 3.06 1.86 3.75 3.64 3.95-.23.2-.44.55-.51 1.07-.46.21-1.61.55-2.33-.66-.15-.24-.6-.83-1.23-.82-.67.01-.27.38.01.53.34.19.73.9.82 1.13.16.45.68 1.31 2.69.94 0 .67.01 1.3.01 1.49 0 .21-.15.45-.55.38A7.995 7.995 0 0 1 0 8c0-4.42 3.58-8 8-8Z">
                </path>
-            </svg> Code
+            </svg> Community

        </a>
-
    </div>
+
    <!-- <script type="module" src="https://cdn.bootcdn.net/ajax/libs/photoswipe/5.4.0/photoswipe-lightbox.esm.min.js"></script> -->
    <script type="module">
        import PhotoSwipeLightbox from '/extensions/comfyui-mixlab-nodes/lib/photoswipe-lightbox.esm.min.js'
@@ -406,8 +444,164 @@

            return { url: src, name }

+        };
+
+
+        function base64ToBlob(base64) {
+            // 去除base64编码中的前缀
+            const base64WithoutPrefix = base64.replace(/^data:image\/\w+;base64,/, '');
+
+            // 将base64编码转换为字节数组
+            const byteCharacters = atob(base64WithoutPrefix);
+
+            // 创建一个存储字节数组的数组
+            const byteArrays = [];
+
+            // 将字节数组放入数组中
+            for (let offset = 0; offset < byteCharacters.length; offset += 1024) {
+                const slice = byteCharacters.slice(offset, offset + 1024);
+
+                const byteNumbers = new Array(slice.length);
+                for (let i = 0; i < slice.length; i++) {
+                    byteNumbers[i] = slice.charCodeAt(i);
+                }
+
+                const byteArray = new Uint8Array(byteNumbers);
+                byteArrays.push(byteArray);
+            }
+
+            // 创建blob对象
+            const blob = new Blob(byteArrays, { type: 'image/png' }); // 根据实际情况设置MIME类型
+
+            return blob;
        }

+
+        function editImage(img, data) {
+
+
+            const update = async () => {
+                const { imageData } = filerobotImageEditor.getCurrentImgData()
+                let base64 = imageData.imageBase64;
+
+                let fileBlob = base64ToBlob(base64)
+                // // 获取读取的文件内容，即 Blob 对象
+                let hashId = await calculateImageHash(fileBlob)
+
+                if (hashId == window._appData.data[data.id].hashId) return
+
+                let { url, name } = await uploadImage(fileBlob);
+                // 在这里可以对 Blob 对象进行进一步处理
+                // imageElement.src = url;
+                window._appData.data[data.id].inputs.image = name;
+                window._appData.data[data.id].hashId = hashId;
+
+                console.log("上传的文件：", url, data.id, name);
+
+                img.src = base64;
+            }
+
+            const { TABS, TOOLS } = FilerobotImageEditor;
+            const config = {
+                source: img.src,
+                // loadableDesignState:{ //默认值
+                //     annotations:{
+                //         watermark:{
+                //             image:'https://127.0.0.1:8189/view?filename=1703554480406.png&type=input&subfolder=&rand=0.044164708320141965',
+                //             width:100,
+                //             height:200,
+                //             x:10,
+                //             y:50,
+                //             name: "Image",
+                //             id:'watermark'
+                //         }
+                //     }
+                // },
+                // annotationsCommon: {
+                //     fill: '#ff0000',
+                // },
+                // Text: { text: 'Filerobot...' },
+                Rotate: { angle: 90, componentType: 'slider' },
+
+                Crop: {
+                    presetsItems: [
+                        {
+                            titleKey: 'classicTv',
+                            descriptionKey: '4:3',
+                            ratio: 4 / 3,
+                            // icon: CropClassicTv,  
+                        },
+                        {
+                            titleKey: 'cinemascope',
+                            descriptionKey: '21:9',
+                            ratio: 21 / 9,
+                            // icon: CropCinemaScope, 
+                        },
+                    ],
+                    presetsFolders: [
+                        {
+                            titleKey: 'socialMedia', // will be translated into Social Media as backend contains this translation key
+                            // icon: Social, // optional,  
+                            groups: [
+                                {
+                                    titleKey: 'facebook',
+                                    items: [
+                                        {
+                                            titleKey: 'profile',
+                                            width: 180,
+                                            height: 180,
+                                            descriptionKey: 'fbProfileSize',
+                                        },
+                                        {
+                                            titleKey: 'coverPhoto',
+                                            width: 820,
+                                            height: 312,
+                                            descriptionKey: 'fbCoverPhotoSize',
+                                        },
+                                    ],
+                                },
+                            ],
+                        },
+                    ],
+                },
+                tabsIds: [...Object.values(TABS)], // or ['Adjust', 'Annotate', 'Watermark']
+                defaultTabId: TABS.WATERMARK, // or 'Annotate'
+                defaultToolId: TOOLS.WATERMARK, // or 'Text'
+                closeAfterSave: true
+            };
+
+            let editor = document.querySelector('#editor_container')
+            // Assuming we have a div with id="editor_container"
+            editor.style.display = 'block';
+            // console.log(img,editor,data)
+            document.body.style.overflow = 'hidden'
+
+            const filerobotImageEditor = new FilerobotImageEditor(
+                editor,
+                config,
+            );
+
+            filerobotImageEditor.render({
+                onSave: (editedImageObject, designState) => {
+                    console.log('saved', designState)
+                    //adjustments
+                    update()
+                },
+                onClose: (closingReason) => {
+                    console.log('Closing reason', closingReason);
+
+                    filerobotImageEditor.terminate();
+                    editor.style.display = 'none'
+                    document.body.style.overflow = 'auto'
+
+                },
+            });
+
+        }
+
+
+
+
        async function getQueue(clientId) {
            try {

@@ -567,19 +761,44 @@
            } catch (error) {
                isURL = false;
            }
+
+            let isAElement = undefined;
+            try {
+                let div = document.createElement('div');
+                div.innerHTML = link;
+                let a = div.querySelector('a');
+                if (a.href) {
+                    new URL(a.href);
+                    isAElement = div.innerHTML;
+                }
+            } catch (error) {
+
+            }
            // new URL(link)
-            if (isURL) {
+            if (isURL || isAElement) {
                const linkBtn = document.createElement('button');
-                // linkBtn.href = link;
-                linkBtn.innerText = 'go to'
+
+                if (isURL) {
+                    // linkBtn.href = link;
+                    linkBtn.innerText = 'go to'
+                } else if (isAElement) {
+                    linkBtn.innerHTML = isAElement
+                }
+
                action.appendChild(linkBtn)
                linkBtn.style.marginLeft = '18px';
                linkBtn.addEventListener('click', e => {
-                    e.preventDefault();
-                    window.open(link);
+
+                    if (isURL) {
+                        e.preventDefault();
+                        window.open(link);
+                    }
+                    //   if(isURL)  window.open(link);
                })
+
            }

+
            const output_card = document.createElement("div");
            output_card.className = 'output_card'
            container.appendChild(output_card)
@@ -892,6 +1111,12 @@
                    btnFromClipboard.innerText = 'paste from clipboard'
                    actionDiv.appendChild(btnFromClipboard);

+                    const btnForImageEdit = document.createElement("button");
+                    btnForImageEdit.style = ` width: 32px; background: none;margin-left: 18px;`
+                    btnForImageEdit.innerHTML = '<?xml version="1.0" ?><svg version="1.1" style="width: 24px;" viewBox="0 0 50 50" xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="Layer_1_1_"><path d="M18.293,31.707h6.414l24-24l-6.414-6.414l-24,24V31.707z M45.879,7.707l-3.586,3.586l-3.586-3.586l3.586-3.586   L45.879,7.707z M20.293,26.121l17-17l3.586,3.586l-17,17h-3.586V26.121z"/><polygon points="43.293,19.707 41.293,19.707 41.293,46.707 3.293,46.707 3.293,8.707 31.293,8.707 31.293,6.707 1.293,6.707    1.293,48.707 43.293,48.707  "/></g></svg>'
+                    actionDiv.appendChild(btnForImageEdit);
+
+
                    uploadContainer.appendChild(actionDiv)

                    // Create an image element to display the uploaded image
@@ -902,6 +1127,8 @@

                    btnFromClipboard.addEventListener('click', (event) => handleClipboardImage(imageElement, data));

+                    btnForImageEdit.addEventListener('click', e => editImage(imageElement, data))
+

                    uploadImageInput.addEventListener('click', (event) => {
                        uploadImageInputHide.click()
@@ -1624,6 +1851,7 @@
                                    p.className = 'prompt_image'
                                    p.innerText = prompt;
                                    a.appendChild(p)
+                                    img.alt = prompt
                                }

                                // imgDiv.parentElement.appendChild(a);
@@ -1931,6 +2159,36 @@
                children: 'a',
                pswpModule: () => import('/extensions/comfyui-mixlab-nodes/lib/photoswipe.esm.min.js')
            });
+            lightbox.on('uiRegister', function () {
+                lightbox.pswp.ui.registerElement({
+                    name: 'custom-caption',
+                    order: 9,
+                    isButton: false,
+                    appendTo: 'root',
+                    html: 'Caption text',
+                    onInit: (el, pswp) => {
+                        lightbox.pswp.on('change', () => {
+                            const currSlideElement = lightbox.pswp.currSlide.data.element
+                            let captionHTML = ''
+                            if (currSlideElement) {
+                                const hiddenCaption = currSlideElement.querySelector(
+                                    '.hidden-caption-content'
+                                )
+                                if (hiddenCaption) {
+                                    // get caption from element with class hidden-caption-content
+                                    captionHTML = hiddenCaption.innerHTML
+                                } else {
+                                    // get caption from alt attribute
+                                    captionHTML = currSlideElement
+                                        .querySelector('img')
+                                        .getAttribute('alt')
+                                }
+                            }
+                            el.innerHTML = captionHTML || ''
+                        })
+                    }
+                })
+            })
            lightbox.init();
            // window._lightbox = lightbox

@@ -2006,13 +2264,14 @@

            createApp(window._appData);

-
        };

-        init_app()
-    </script>
+        init_app();


+
+    </script>
+
 </body>

 </html>
@@ -100,16 +100,17 @@ function extractInputAndOutputData (jsonData, inputIds = [], outputIds = []) {
          // min max step
          options = node.widgets.filter(w => w.type === 'slider')[0].options
          // 备选的keywords清单
-          let ks = getLocalData(`_mixlab_PromptSlide`)
-          let keywords = ks[id]
-          // console.log('keywords',keywords)
-          if (keywords && keywords[0]) {
+          try {
+            let keywords = node.widgets.filter(w => w.name === 'upload')[0]
+              .value
+            keywords = JSON.parse(keywords)
            options.keywords = keywords
+          } catch (error) {
+            console.log(error)
          }
        }

-        if(node.type=='Color'){
-          
+        if (node.type == 'Color') {
        }

        input[inputIds.indexOf(id)] = {
@@ -126,11 +127,11 @@ function extractInputAndOutputData (jsonData, inputIds = [], outputIds = []) {
        output[outputIds.indexOf(id)] = { ...data[id], title: node.title, id }
      }

-      if (node.type === 'KSampler'||node.type=='SamplerCustom') {
+      if (node.type === 'KSampler' || node.type == 'SamplerCustom') {
        // seed 的类型收集
        try {
          seed[id] = node.widgets.filter(
-            w => (w.name === 'seed'||w.name=='noise_seed')
+            w => w.name === 'seed' || w.name == 'noise_seed'
          )[0].linkedWidgets[0].value
        } catch (error) {}
      }
@@ -188,7 +189,8 @@ function downloadJsonFile (jsonData, fileName = 'mix_app.json') {
  }, 0)
 }

-async function save (json, download = false) {
+async function save (json, download = false, showInfo = true) {
+  console.log('####SAVE', json[0])
  const name = json[0],
    version = json[5],
    share_prefix = json[6], //用于分享的功能扩展
@@ -237,22 +239,53 @@ async function save (json, download = false) {
    if (download) {
      await downloadJsonFile(data, data.app.filename)
    }
-    let open = window.confirm(
-      `You can now access the standalone application on a new page!\n${getUrl()}/mixlab/app?filename=${encodeURIComponent(
-        data.app.filename
-      )}&category=${encodeURIComponent(data.app.category)}`
-    )
-    if (open)
-      window.open(
-        `${getUrl()}/mixlab/app?filename=${encodeURIComponent(
+
+    if (showInfo) {
+      let open = window.confirm(
+        `You can now access the standalone application on a new page!\n${getUrl()}/mixlab/app?filename=${encodeURIComponent(
          data.app.filename
        )}&category=${encodeURIComponent(data.app.category)}`
      )
+      if (open)
+        window.open(
+          `${getUrl()}/mixlab/app?filename=${encodeURIComponent(
+            data.app.filename
+          )}&category=${encodeURIComponent(data.app.category)}`
+        )
+    }
  } catch (error) {
    console.log('###error', error)
  }
 }

+function getInputsAndOutputs () {
+  const inputs =
+      `LoadImage CLIPTextEncode PromptSlide TextInput_ Color FloatSlider IntNumber CheckpointLoaderSimple LoraLoader`.split(
+        ' '
+      ),
+    outputs = `PreviewImage SaveImage ShowTextForGPT VHS_VideoCombine`.split(
+      ' '
+    )
+
+  let inputsId = [],
+    outputsId = []
+
+  for (let node of app.graph._nodes) {
+    if (inputs.includes(node.type)) {
+      inputsId.push(node.id)
+    }
+
+    if (outputs.includes(node.type)) {
+      outputsId.push(node.id)
+    }
+  }
+
+  return {
+    input: inputsId,
+    output: outputsId
+  }
+}
+
 app.registerExtension({
  name: 'Mixlab.utils.AppInfo',
  async beforeRegisterNodeDef (nodeType, nodeData, app) {
@@ -260,7 +293,16 @@ app.registerExtension({
      const orig_nodeCreated = nodeType.prototype.onNodeCreated
      nodeType.prototype.onNodeCreated = function () {
        orig_nodeCreated?.apply(this, arguments)
-        console.log('#orig_nodeCreated', this)
+        // console.log('#orig_nodeCreated', this)
+
+        // 自动计算workflow里哪些节点支持
+        let input_ids = this.widgets.filter(w => w.name == 'input_ids')[0],
+          output_ids = this.widgets.filter(w => w.name == 'output_ids')[0]
+
+        const { input, output } = getInputsAndOutputs()
+        input_ids.value = input.join('\n')
+        output_ids.value = output.join('\n')
+
        const widget = {
          type: 'div',
          name: 'AppInfoRun',
@@ -331,6 +373,8 @@ app.registerExtension({
        }

        this.serialize_widgets = true //需要保存参数
+
+        window._mixlab_app_json = null
      }

      const onExecuted = nodeType.prototype.onExecuted
@@ -339,6 +383,12 @@ app.registerExtension({
        console.log(message.json)
        window._mixlab_app_json = message.json
        try {
+          let a = this.widgets.filter(w => w.name === 'AppInfoRun')[0]
+          if (a) {
+            if (!a.value) a.value = 0
+            a.value += 1
+          }
+
          const div = this.widgets.filter(w => w.div)[0].div
          Array.from(
            div.querySelectorAll('button'),
@@ -347,5 +397,39 @@ app.registerExtension({
        } catch (error) {}
      }
    }
+  },
+  async loadedGraphNode (node, app) {
+    console.log('#loadedGraphNode1111')
+    window._mixlab_app_json = null //切换workflow需要清空
+    if (node.type === 'AppInfo') {
+      let auto_save = node.widgets.filter(w => w.name == 'auto_save')[0]
+      if (auto_save) {
+        if (!['enable', 'disable'].includes(auto_save.value)) {
+          auto_save.value = 'enable'
+        }
+      }
+    }
+  }
+})
+
+api.addEventListener('execution_start', async ({ detail }) => {
+  console.log('#execution_start', detail)
+  window._mixlab_app_json = null
+})
+
+api.addEventListener('executed', async ({ detail }) => {
+  console.log('#executed', detail)
+  // window._mixlab_app_json=null;
+  const { output } = getInputsAndOutputs()
+  if (output.includes(parseInt(detail.node))) {
+    let appinfo = app.graph.findNodesByType('AppInfo')[0]
+    if (appinfo) {
+      let auto_save = appinfo.widgets.filter(w => w.name == 'auto_save')[0]
+      if (auto_save?.value === 'enable') {
+        // 自动保存
+        console.log('auto_save')
+        if (window._mixlab_app_json) save(window._mixlab_app_json, false, false)
+      }
+    }
  }
 })
@@ -3,7 +3,7 @@ import { app } from '../../../scripts/app.js'
 const repoOwner = 'shadowcz007' // 替换为仓库的所有者
 const repoName = 'comfyui-mixlab-nodes' // 替换为仓库的名称

-const version = 'v0.11.0'
+const version = 'v0.14.0'

 fetch(`https://api.github.com/repos/${repoOwner}/${repoName}/releases/latest`)
  .then(response => response.json())
@@ -3,11 +3,57 @@ import { app } from '../../../scripts/app.js'
 import { ComfyWidgets } from '../../../scripts/widgets.js'
 import { $el } from '../../../scripts/ui.js'

+function getRandomElements (arr, num) {
+  var result = []
+  var len = arr.length
+
+  for (var i = 0; i < num; i++) {
+    var randomIndex = Math.floor(Math.random() * len)
+    result.push(arr[randomIndex])
+  }
+
+  return result
+}
+
+const createPrompt = (node, prompts, items, sample) => {
+  const w = ComfyWidgets['STRING'](
+    node,
+    'text',
+    ['STRING', { multiline: true }],
+    app
+  ).widget
+  w.inputEl.readOnly = true
+  w.inputEl.style.opacity = 0.6
+
+  w.value = typeof prompts === 'string' ? prompts : prompts.join('\n\n')
+
+  const w2 = ComfyWidgets['STRING'](
+    node,
+    'text',
+    ['STRING', { multiline: true }],
+    app
+  ).widget
+  w2.inputEl.readOnly = true
+  w2.inputEl.style.opacity = 0.6
+
+  w2.value = typeof items === 'string' ? items : JSON.stringify(items, null, 2)
+
+  const w3 = ComfyWidgets['STRING'](
+    node,
+    'text',
+    ['STRING', { multiline: true }],
+    app
+  ).widget
+  w3.inputEl.readOnly = true
+  w3.inputEl.style.opacity = 0.6
+  w3.value = typeof sample === 'string' ? sample : sample.join('\n\n')
+}
+
 app.registerExtension({
  name: 'Mixlab.prompt.ClipInterrogator',
  async beforeRegisterNodeDef (nodeType, nodeData, app) {
    if (nodeData.name === 'ClipInterrogator') {
-      function populate (prompts, items) {
+      function populate (prompts, items, random_samples) {
        if (this.widgets) {
          for (let i = 0; i < this.widgets.length; i++) {
            if (this.widgets[i].type !== 'combo') this.widgets[i].onRemove?.()
@@ -15,29 +61,9 @@ app.registerExtension({
          this.widgets.length = 2
        }

-        const w = ComfyWidgets['STRING'](
-          this,
-          'text',
-          ['STRING', { multiline: true }],
-          app
-        ).widget
-        w.inputEl.readOnly = true
-        w.inputEl.style.opacity = 0.6
+        createPrompt(this, prompts, items, random_samples)

-        w.value = prompts.join('\n\n')
-
-        const w2 = ComfyWidgets['STRING'](
-          this,
-          'text',
-          ['STRING', { multiline: true }],
-          app
-        ).widget
-        w2.inputEl.readOnly = true
-        w2.inputEl.style.opacity = 0.6
-
-        w2.value = JSON.stringify(items, null, 2)
-
-        console.log('ClipInterrogator',w,w2)
+        // console.log('ClipInterrogator', w, w2)
        requestAnimationFrame(() => {
          const sz = this.computeSize()
          if (sz[0] < this.size[0]) {
@@ -55,11 +81,39 @@ app.registerExtension({
      const onExecuted = nodeType.prototype.onExecuted
      nodeType.prototype.onExecuted = function (message) {
        onExecuted?.apply(this, arguments)
-        console.log('##', message)
-        populate.call(this, message.prompt, message.analysis)
+        // console.log('##', message)
+        populate.call(
+          this,
+          message.prompt,
+          message.analysis,
+          message.random_samples
+        )
      }

      this.serialize_widgets = true //需要保存参数
    }
+  },
+  async loadedGraphNode (node, app) {
+    // Fires every time a node is constructed
+    // You can modify widgets/add handlers/etc here
+
+    if (node.type === 'ClipInterrogator') {
+      try {
+        
+        let widgets_values = node.widgets_values
+        console.log(widgets_values )
+        try {
+          if (widgets_values[2] && widgets_values[3] && widgets_values[4])
+            createPrompt(
+              node,
+              widgets_values[2],
+              widgets_values[3],
+              widgets_values[4]
+            )
+        } catch (error) {
+          console.log(error)
+        }
+      } catch (error) {}
+    }
  }
 })
@@ -1331,7 +1331,13 @@ app.registerExtension({
          let w = 360,
            s = widget.preview.videoWidth / widget.preview.videoHeight,
            h = w / s || w
-          console.log(h)
+          // console.log(h)
+
+          if (!window.documentPictureInPicture) {
+            window.alert(
+              'This feature is available only in secure contexts (HTTPS), in some or all supporting browsers. https://developer.mozilla.org/en-US/docs/Web/API/Document_Picture-in-Picture_API'
+            )
+          }

          const pipWindow = await documentPictureInPicture.requestWindow({
            width: w,
@@ -2137,8 +2143,8 @@ const node = {
  loadedGraphNode (node, app) {
    if (node.type === 'RandomPrompt') {
      try {
-        let max_count = node.widgets.filter(w => w.name === "max_count")[0];
-        max_count.value= node.widgets_values[0]
+        let max_count = node.widgets.filter(w => w.name === 'max_count')[0]
+        max_count.value = node.widgets_values[0]
        // console.log('RandomPrompt',max_count,node.widgets_values[0])
      } catch (error) {
        console.log(error)
@@ -3,6 +3,87 @@ import { api } from '../../../scripts/api.js'
 import { ComfyWidgets } from '../../../scripts/widgets.js'
 import { $el } from '../../../scripts/ui.js'

+import PhotoSwipeLightbox from '/extensions/comfyui-mixlab-nodes/lib/photoswipe-lightbox.esm.min.js'
+function loadCSS (url) {
+  var link = document.createElement('link')
+  link.rel = 'stylesheet'
+  link.type = 'text/css'
+  link.href = url
+  document.getElementsByTagName('head')[0].appendChild(link)
+
+  // Create a style element
+  const style = document.createElement('style')
+  // Define the CSS rule for scrollbar width
+  const cssRule = `.pswp__custom-caption {
+    background: rgb(20 27 70);
+    font-size: 16px;
+    color: #fff;
+    width: calc(100% - 32px);
+    max-width: 980px;
+    padding: 2px 8px;
+    border-radius: 4px;
+    position: absolute;
+    left: 50%;
+    bottom: 16px;
+    transform: translateX(-50%);
+  }
+  .pswp__custom-caption a {
+    color: #fff;
+    text-decoration: underline;
+  }
+  .hidden-caption-content {
+    display: none;
+  }`
+  // Add the CSS rule to the style element
+  style.appendChild(document.createTextNode(cssRule))
+
+  // Append the style element to the document head
+  document.head.appendChild(style)
+}
+loadCSS('/extensions/comfyui-mixlab-nodes/lib/photoswipe.min.css')
+
+function initLightBox () {
+  const lightbox = new PhotoSwipeLightbox({
+    gallery: '.prompt_image_output',
+    children: 'a',
+    pswpModule: () =>
+      import('/extensions/comfyui-mixlab-nodes/lib/photoswipe.esm.min.js')
+  })
+
+  lightbox.on('uiRegister', function () {
+    lightbox.pswp.ui.registerElement({
+      name: 'custom-caption',
+      order: 9,
+      isButton: false,
+      appendTo: 'root',
+      html: 'Caption text',
+      onInit: (el, pswp) => {
+        lightbox.pswp.on('change', () => {
+          const currSlideElement = lightbox.pswp.currSlide.data.element
+          let captionHTML = ''
+          if (currSlideElement) {
+            const hiddenCaption = currSlideElement.querySelector(
+              '.hidden-caption-content'
+            )
+            if (hiddenCaption) {
+              // get caption from element with class hidden-caption-content
+              captionHTML = hiddenCaption.innerHTML
+            } else {
+              // get caption from alt attribute
+              captionHTML = currSlideElement
+                .querySelector('img')
+                .getAttribute('alt')
+            }
+          }
+          el.innerHTML = captionHTML || ''
+        })
+      }
+    })
+  })
+
+  lightbox.init()
+}
+
 function get_position_style (ctx, widget_width, y, node_height) {
  const MARGIN = 4 // the margin around the html element

@@ -97,8 +178,7 @@ app.registerExtension({
      const orig_nodeCreated = nodeType.prototype.onNodeCreated
      nodeType.prototype.onNodeCreated = async function () {
        orig_nodeCreated?.apply(this, arguments)
-        name
-
+         
        const mutable_prompt = this.widgets.filter(
          w => w.name == 'mutable_prompt'
        )[0]
@@ -186,16 +266,7 @@ app.registerExtension({
  },
  async loadedGraphNode (node, app) {
    if (node.type === 'RandomPrompt') {
-      // try {
-      //   let mutable_prompt = node.widgets.filter(w => w.name === 'mutable_prompt')[0]
-      //   // let ks = getLocalData(`_mixlab_PromptSlide`)
-      //   let uploadWidget = node.widgets.filter(w => w.name == 'upload')[0]
-      //   // console.log('##widget', uploadWidget.value)
-      //   let keywords = JSON.parse(uploadWidget.value)
-      //   if (keywords && keywords[0]) {
-      //     mutable_prompt.value=keywords.join('\n')
-      //   }
-      // } catch (error) {}
+     
    }
  }
 })
@@ -381,11 +452,19 @@ const _createResult = async (node, widget, message) => {
      let h = (image.naturalHeight * width) / image.naturalWidth
      if (index % 2 === 0) height_add += h
      div.style = `width: ${width}px;height:${h}px;position: relative;margin: 4px;`
-      div.innerHTML = `<img src="${url}" style='width: 100%'/>
-            <p style="position: absolute;
+
+      div.innerHTML = `<a href="${url}" 
+      data-pswp-width="${image.naturalWidth}" 
+      data-pswp-height="${image.naturalHeight}" 
+      target="_blank">
+      <img src="${url}" style='width: 100%' alt="${message.prompts[index]}"/>
+    </a>
+    <p style="position: absolute;
            bottom: 0;
-            left: 0; 
-            background:#444444c2;
+            left: 0;
+            opacity: 0.6;
+            background-color: var(--comfy-input-bg); 
+            color: var(--descrip-text);
            margin: 0;
            font-size: 12px;
            padding: 5px;
@@ -422,11 +501,14 @@ app.registerExtension({
        }

        widget.div = $el('div', {})
+        widget.div.className = 'prompt_image_output'

        document.body.appendChild(widget.div)

        this.addCustomWidget(widget)

+        initLightBox()
+
        const onRemoved = this.onRemoved
        this.onRemoved = () => {
          widget.div.remove()
@@ -472,6 +554,9 @@ app.registerExtension({
      // await sleep(0)
      let widget = node.widgets.filter(w => w.name === 'result')[0]
      console.log('widget.value', widget.value)
+
+      initLightBox()
+
      let cards = widget.div.querySelectorAll('.card')
      if (cards.length == 0) node.size = [280, 120]

@@ -739,8 +739,9 @@ app.registerExtension({
        if (category === '0') {
          apps_opts.push(
            ...Array.from(apps_map[category], a => {
+              // console.log('#1级',a)
              return {
-                content: a.name,
+                content: `${a.name}_${a.version}`,
                has_submenu: false,
                callback: async () => {
                  try {
@@ -768,8 +769,9 @@ app.registerExtension({
            disabled: false,
            submenu: {
              options: Array.from(apps_map[category], a => {
+                // console.log('#二级',a)
                return {
-                  content: a.name,
+                  content: `${a.name}_${a.version}`,
                  callback: async () => {
                    try {
                      let item = (await get_my_app(a.filename, a.category))[0]
@@ -269,7 +269,6 @@ app.registerExtension({
          const n = this.widgets.filter(w => w.name === 'number')[0]
          n.value = message.num[0]
        }
-
        console.log('TextToNumber', random_number.value)
      }
    }
@@ -307,11 +306,16 @@ const min_max = node => {
 app.registerExtension({
  name: 'Mixlab.utils.FloatSlider',
  async beforeRegisterNodeDef (nodeType, nodeData, app) {
-    const orig_nodeCreated = nodeType.prototype.onNodeCreated
-    nodeType.prototype.onNodeCreated = function () {
-      orig_nodeCreated?.apply(this, arguments)
-      min_max(this)
+
+    if (nodeType.comfyClass == 'FloatSlider') {
+      const orig_nodeCreated = nodeType.prototype.onNodeCreated;
+      nodeType.prototype.onNodeCreated = function () {
+        orig_nodeCreated?.apply(this, arguments)
+        min_max(this)
+      }
    }
+
+   
  },
  async loadedGraphNode (node, app) {
    if (node.type === 'FloatSlider') {
@@ -322,11 +326,15 @@ app.registerExtension({
 app.registerExtension({
  name: 'Mixlab.utils.IntNumber',
  async beforeRegisterNodeDef (nodeType, nodeData, app) {
-    const orig_nodeCreated = nodeType.prototype.onNodeCreated
-    nodeType.prototype.onNodeCreated = function () {
-      orig_nodeCreated?.apply(this, arguments)
-      min_max(this)
+    
+    if (nodeType.comfyClass == 'IntNumber') {
+      const orig_nodeCreated = nodeType.prototype.onNodeCreated
+      nodeType.prototype.onNodeCreated = function () {
+        orig_nodeCreated?.apply(this, arguments)
+        min_max(this)
+      }
    }
+   
  },
  async loadedGraphNode (node, app) {
    if (node.type === 'IntNumber') {
@@ -334,3 +342,23 @@ app.registerExtension({
    }
  }
 })
+
+
+app.registerExtension({
+  name: 'Mixlab.utils.TESTNODE_',
+  async beforeRegisterNodeDef (nodeType, nodeData, app) {
+    
+    if (nodeType.comfyClass == 'TESTNODE_') {
+    
+      const onExecuted = nodeType.prototype.onExecuted;
+			nodeType.prototype.onExecuted = function (message) {
+				onExecuted?.apply(this, arguments);
+        console.log('##',message)
+				 
+			};
+
+
+    }
+   
+  }, 
+})
@@ -60,30 +60,7 @@ app.registerExtension({
          type: inputData[0], // the type, CHEESE
          name: inputName, // the name, slice
          size: [128, 24], // a default size
-          draw (ctx, node, width, y) {
-            // // 绘制文件图标的函数
-            // function drawFileIcon () {
-            //   // 清空画布
-            //   // ctx.clearRect(0, 0, canvas.width, canvas.height)
-
-            //   // 绘制文件外框
-            //   ctx.fillStyle = '#000'
-            //   ctx.fillRect(5, 5, 40, 40)
-
-            //   // 绘制文件夹图标
-            //   ctx.fillStyle = '#f00'
-            //   ctx.fillRect(10, 15, 30, 20)
-
-            //   // 绘制监听符号
-            //   ctx.beginPath()
-            //   ctx.arc(30, 35, 5, 0, 2 * Math.PI)
-            //   ctx.fillStyle = '#00f'
-            //   ctx.fill()
-            // }
-
-            // // 调用绘制函数
-            // drawFileIcon()
-          },
+          draw (ctx, node, width, y) {},
          computeSize (...args) {
            return [128, 24] // a method to compute the current size of the widget
          },
@@ -124,11 +101,19 @@ app.registerExtension({
      nodeType.prototype.onNodeCreated = function () {
        orig_nodeCreated?.apply(this, arguments)

-        console.log('watch widtget', this.widgets)
+        // 虚拟的widget，用于更新节点，让其每次都运行
+        const widget = {
+          type: 'div',
+          name: 'seed',
+          draw (ctx, node, widget_width, y, widget_height) {}
+        }
+
+        this.addCustomWidget(widget)

        const watcher = this.widgets.filter(w => w.name == 'watcher')[0]

        watcher.callback = () => {
+          console.log('watcher', watcher.value)
          if (watcher.value === 'enable') {
            if (window._mixlab_watcher_t)
              clearInterval(window._mixlab_watcher_t)
@@ -140,7 +125,7 @@ app.registerExtension({
                  window._mixlab_file_path_watcher = json.event_type
                  // widget.card.innerText = window._mixlab_file_path_watcher || ''
                  //运行
-                  document.querySelector('#queue-button').click()
+                  // document.querySelector('#queue-button').click()
                }
              })
            }, 1000)
@@ -162,15 +147,59 @@ app.registerExtension({
          window._mixlab_file_path_watcher = json.event_type
        })

-        /*
-                Add the widget, make sure we clean up nicely, and we do not want to be serialized!
-                */
-        // this.addCustomWidget(widget)
        this.onRemoved = function () {
          // widget.card.remove()
        }
        this.serialize_widgets = true
      }
+
+      const onExecuted = nodeType.prototype.onExecuted
+      nodeType.prototype.onExecuted = function (message) {
+        onExecuted?.apply(this, arguments)
+        console.log(message)
+        try {
+          let seed = this.widgets.filter(w => w.name === 'seed')[0]
+          if (seed) {
+            if (!seed.value) seed.value = 0
+            seed.value += 1
+          }
+        } catch (error) {}
+      }
+    }
+  },
+  async loadedGraphNode (node, app) {
+    if (node.type === 'LoadImagesFromPath') {
+      const watcher = node.widgets.filter(w => w.name == 'watcher')[0]
+      if (watcher) {
+        if (watcher.value === 'enable') {
+          if (window._mixlab_watcher_t) clearInterval(window._mixlab_watcher_t)
+          window._mixlab_watcher_t = setInterval(() => {
+            // 上次路径填充
+            getConfig().then(json => {
+              console.log(json.event_type)
+              if (json.event_type != window._mixlab_file_path_watcher) {
+                window._mixlab_file_path_watcher = json.event_type
+                // widget.card.innerText = window._mixlab_file_path_watcher || ''
+                //运行
+                document.querySelector('#queue-button').click()
+              }
+            })
+          }, 1000)
+        } else {
+          if (window._mixlab_watcher_t) {
+            clearInterval(window._mixlab_watcher_t)
+          }
+          window._mixlab_watcher_t = null
+        }
+      }
+
+      try {
+        let seed = node.widgets.filter(w => w.name === 'seed')[0]
+        if (seed) {
+          if (!seed.value) seed.value = 0
+          seed.value += 1
+        }
+      } catch (error) {}
    }
  }
 })
@@ -0,0 +1,736 @@
+{
+  "last_node_id": 29,
+  "last_link_id": 32,
+  "nodes": [
+    {
+      "id": 7,
+      "type": "CLIPTextEncode",
+      "pos": [
+        108,
+        316
+      ],
+      "size": {
+        "0": 425.27801513671875,
+        "1": 180.6060791015625
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 16
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            6
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "text, watermark"
+      ]
+    },
+    {
+      "id": 18,
+      "type": "ControlNetApply",
+      "pos": [
+        485,
+        792
+      ],
+      "size": {
+        "0": 317.4000244140625,
+        "1": 98
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "conditioning",
+          "type": "CONDITIONING",
+          "link": 22,
+          "slot_index": 0
+        },
+        {
+          "name": "control_net",
+          "type": "CONTROL_NET",
+          "link": 18,
+          "slot_index": 1
+        },
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 26
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            21
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ControlNetApply"
+      },
+      "widgets_values": [
+        1
+      ]
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": [
+        117,
+        95
+      ],
+      "size": {
+        "0": 422.84503173828125,
+        "1": 164.31304931640625
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 15
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            22
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "a future city,buiding,future,magic,under water"
+      ]
+    },
+    {
+      "id": 15,
+      "type": "LoraLoader",
+      "pos": [
+        116,
+        -113
+      ],
+      "size": {
+        "0": 315,
+        "1": 126
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 13
+        },
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 14
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            12,
+            23
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            15,
+            16
+          ],
+          "shape": 3,
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoraLoader"
+      },
+      "widgets_values": [
+        "lcm-lora-sdv1-5.safetensors",
+        1,
+        1
+      ]
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        -380,
+        185
+      ],
+      "size": {
+        "0": 315,
+        "1": 98
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            13
+          ],
+          "slot_index": 0
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            14
+          ],
+          "slot_index": 1
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            8
+          ],
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "deliberate_v2.safetensors"
+      ]
+    },
+    {
+      "id": 19,
+      "type": "DiffControlNetLoader",
+      "pos": [
+        40,
+        792
+      ],
+      "size": {
+        "0": 367.8165283203125,
+        "1": 58.083831787109375
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 23,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONTROL_NET",
+          "type": "CONTROL_NET",
+          "links": [
+            18
+          ],
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "DiffControlNetLoader"
+      },
+      "widgets_values": [
+        "control_v11f1p_sd15_depth.pth"
+      ]
+    },
+    {
+      "id": 5,
+      "type": "EmptyLatentImage",
+      "pos": [
+        65,
+        573
+      ],
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            2
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        512,
+        512,
+        1
+      ]
+    },
+    {
+      "id": 25,
+      "type": "LeReS-DepthMapPreprocessor",
+      "pos": [
+        47,
+        904
+      ],
+      "size": {
+        "0": 369.6000061035156,
+        "1": 130
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 31
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            26,
+            27
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LeReS-DepthMapPreprocessor"
+      },
+      "widgets_values": [
+        0.1,
+        0,
+        "disable",
+        512
+      ]
+    },
+    {
+      "id": 3,
+      "type": "KSampler",
+      "pos": [
+        1100,
+        -97
+      ],
+      "size": {
+        "0": 315,
+        "1": 262
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 12,
+          "slot_index": 0
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 21
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 6
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 2
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            7
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        170633013599955,
+        "fixed",
+        4,
+        1.6,
+        "lcm",
+        "simple",
+        1
+      ]
+    },
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": [
+        1100,
+        -241
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 8
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            28
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 20,
+      "type": "PreviewImage",
+      "pos": [
+        492,
+        955
+      ],
+      "size": {
+        "0": 526.9624633789062,
+        "1": 367.3833923339844
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 27
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      }
+    },
+    {
+      "id": 26,
+      "type": "FloatingVideo",
+      "pos": [
+        1565,
+        -181
+      ],
+      "size": [
+        315,
+        58
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 28
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "FloatingVideo"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
+    {
+      "id": 28,
+      "type": "PreviewImage",
+      "pos": [
+        -241,
+        953
+      ],
+      "size": {
+        "0": 210,
+        "1": 246
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 32
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      }
+    },
+    {
+      "id": 29,
+      "type": "ScreenShare",
+      "pos": [
+        -639,
+        366
+      ],
+      "size": [
+        315,
+        644
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            31,
+            32
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "PROMPT",
+          "type": "STRING",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "FLOAT",
+          "type": "FLOAT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "INT",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ScreenShare"
+      },
+      "widgets_values": [
+        null,
+        500,
+        null,
+        null,
+        null,
+        null
+      ]
+    }
+  ],
+  "links": [
+    [
+      2,
+      5,
+      0,
+      3,
+      3,
+      "LATENT"
+    ],
+    [
+      6,
+      7,
+      0,
+      3,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      7,
+      3,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      8,
+      4,
+      2,
+      8,
+      1,
+      "VAE"
+    ],
+    [
+      12,
+      15,
+      0,
+      3,
+      0,
+      "MODEL"
+    ],
+    [
+      13,
+      4,
+      0,
+      15,
+      0,
+      "MODEL"
+    ],
+    [
+      14,
+      4,
+      1,
+      15,
+      1,
+      "CLIP"
+    ],
+    [
+      15,
+      15,
+      1,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      16,
+      15,
+      1,
+      7,
+      0,
+      "CLIP"
+    ],
+    [
+      18,
+      19,
+      0,
+      18,
+      1,
+      "CONTROL_NET"
+    ],
+    [
+      21,
+      18,
+      0,
+      3,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      22,
+      6,
+      0,
+      18,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      23,
+      15,
+      0,
+      19,
+      0,
+      "MODEL"
+    ],
+    [
+      26,
+      25,
+      0,
+      18,
+      2,
+      "IMAGE"
+    ],
+    [
+      27,
+      25,
+      0,
+      20,
+      0,
+      "IMAGE"
+    ],
+    [
+      28,
+      8,
+      0,
+      26,
+      0,
+      "IMAGE"
+    ],
+    [
+      31,
+      29,
+      0,
+      25,
+      0,
+      "IMAGE"
+    ],
+    [
+      32,
+      29,
+      0,
+      28,
+      0,
+      "IMAGE"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {},
+  "version": 0.4
+}
@@ -1,6 +1,6 @@
 {
-  "last_node_id": 23,
-  "last_link_id": 51,
+  "last_node_id": 22,
+  "last_link_id": 48,
  "nodes": [
    {
      "id": 7,
@@ -105,7 +105,7 @@
        {
          "name": "text",
          "type": "STRING",
-          "link": 51,
+          "link": 48,
          "widget": {
            "name": "text"
          }
@@ -295,7 +295,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        482859286431021,
+        644769503212755,
        "randomize",
        4,
        1.6,
@@ -316,19 +316,47 @@
        "1": 246
      },
      "flags": {},
-      "order": 7,
+      "order": 6,
      "mode": 0,
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
-          "link": 50
+          "link": 46
        }
      ],
      "properties": {
        "Node name for S&R": "PreviewImage"
      }
    },
+    {
+      "id": 20,
+      "type": "FloatingVideo",
+      "pos": [
+        2041,
+        277
+      ],
+      "size": [
+        315,
+        58
+      ],
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 41
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "FloatingVideo"
+      },
+      "widgets_values": [
+        null
+      ]
+    },
    {
      "id": 6,
      "type": "LoraLoader",
@@ -445,13 +473,13 @@
        "1": 58
      },
      "flags": {},
-      "order": 6,
+      "order": 7,
      "mode": 0,
      "inputs": [
        {
          "name": "image",
          "type": "IMAGE",
-          "link": 49
+          "link": 47
        }
      ],
      "outputs": [
@@ -473,43 +501,15 @@
      ]
    },
    {
-      "id": 20,
-      "type": "FloatingVideo",
+      "id": 22,
+      "type": "ScreenShare",
      "pos": [
-        1928,
-        295
+        -111,
+        427
      ],
      "size": [
        315,
-        58
-      ],
-      "flags": {},
-      "order": 12,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 41
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "FloatingVideo"
-      },
-      "widgets_values": [
-        null
-      ]
-    },
-    {
-      "id": 23,
-      "type": "ScreenShare",
-      "pos": [
-        -65,
-        446
-      ],
-      "size": [
-        312.78457519531213,
-        606.2132135620109
+        644
      ],
      "flags": {},
      "order": 3,
@@ -519,8 +519,8 @@
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
-            49,
-            50
+            46,
+            47
          ],
          "shape": 3,
          "slot_index": 0
@@ -529,7 +529,7 @@
          "name": "PROMPT",
          "type": "STRING",
          "links": [
-            51
+            48
          ],
          "shape": 3,
          "slot_index": 1
@@ -552,7 +552,7 @@
      },
      "widgets_values": [
        null,
-        2018,
+        500,
        null,
        null,
        null,
@@ -810,24 +810,24 @@
      "CLIP"
    ],
    [
-      49,
-      23,
-      0,
-      18,
-      0,
-      "IMAGE"
-    ],
-    [
-      50,
-      23,
+      46,
+      22,
      0,
      2,
      0,
      "IMAGE"
    ],
    [
-      51,
-      23,
+      47,
+      22,
+      0,
+      18,
+      0,
+      "IMAGE"
+    ],
+    [
+      48,
+      22,
      1,
      8,
      1,
@@ -1,6 +1,6 @@
 {
-  "last_node_id": 128,
-  "last_link_id": 207,
+  "last_node_id": 129,
+  "last_link_id": 208,
  "nodes": [
    {
      "id": 8,
@@ -466,7 +466,7 @@
        "1": 262
      },
      "flags": {},
-      "order": 28,
+      "order": 27,
      "mode": 0,
      "inputs": [
        {
@@ -526,7 +526,7 @@
        "1": 262
      },
      "flags": {},
-      "order": 30,
+      "order": 29,
      "mode": 0,
      "inputs": [
        {
@@ -574,31 +574,6 @@
        ""
      ]
    },
-    {
-      "id": 101,
-      "type": "PreviewImage",
-      "pos": [
-        5328.397364750004,
-        -1726.0537115390628
-      ],
-      "size": {
-        "0": 210,
-        "1": 246
-      },
-      "flags": {},
-      "order": 27,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 161
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "PreviewImage"
-      }
-    },
    {
      "id": 21,
      "type": "Note",
@@ -670,7 +645,7 @@
        "1": 262
      },
      "flags": {},
-      "order": 32,
+      "order": 31,
      "mode": 0,
      "inputs": [
        {
@@ -1148,7 +1123,7 @@
        "1": 46
      },
      "flags": {},
-      "order": 34,
+      "order": 33,
      "mode": 0,
      "inputs": [
        {
@@ -1171,6 +1146,12 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
@@ -1189,7 +1170,7 @@
        "1": 46
      },
      "flags": {},
-      "order": 35,
+      "order": 34,
      "mode": 0,
      "inputs": [
        {
@@ -1212,6 +1193,12 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
@@ -1230,7 +1217,7 @@
        "1": 46
      },
      "flags": {},
-      "order": 36,
+      "order": 35,
      "mode": 0,
      "inputs": [
        {
@@ -1253,6 +1240,12 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
@@ -1304,7 +1297,7 @@
        "1": 532.8897705078125
      },
      "flags": {},
-      "order": 37,
+      "order": 36,
      "mode": 0,
      "inputs": [
        {
@@ -1329,7 +1322,7 @@
        "1": 553.1112670898438
      },
      "flags": {},
-      "order": 38,
+      "order": 37,
      "mode": 0,
      "inputs": [
        {
@@ -1354,7 +1347,7 @@
        "1": 150
      },
      "flags": {},
-      "order": 31,
+      "order": 30,
      "mode": 0,
      "inputs": [
        {
@@ -1464,7 +1457,7 @@
        "1": 499.6607971191406
      },
      "flags": {},
-      "order": 39,
+      "order": 38,
      "mode": 0,
      "inputs": [
        {
@@ -1489,7 +1482,7 @@
        "1": 150
      },
      "flags": {},
-      "order": 33,
+      "order": 32,
      "mode": 0,
      "inputs": [
        {
@@ -1554,7 +1547,7 @@
        "1": 150
      },
      "flags": {},
-      "order": 29,
+      "order": 28,
      "mode": 0,
      "inputs": [
        {
@@ -1705,56 +1698,10 @@
        101,
        0,
        "#000000",
+        false,
        false
      ]
    },
-    {
-      "id": 98,
-      "type": "AppInfo",
-      "pos": [
-        4922.397364750004,
-        -1807.0537115390628
-      ],
-      "size": {
-        "0": 362.42608642578125,
-        "1": 431.3537902832031
-      },
-      "flags": {},
-      "order": 16,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 162
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            161
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AppInfo"
-      },
-      "widgets_values": [
-        "AIPC大赛模板",
-        "\n75\n118",
-        "57\n126\n127\n",
-        "投稿模板#发挥你的想象力",
-        4,
-        "#AIPC# 参赛作品",
-        "https://www.weibo.com",
-        "",
-        null
-      ]
-    },
    {
      "id": 106,
      "type": "LoadImage",
@@ -1762,10 +1709,10 @@
        4535,
        -1843
      ],
-      "size": [
-        210,
-        314
-      ],
+      "size": {
+        "0": 210,
+        "1": 314
+      },
      "flags": {},
      "order": 7,
      "mode": 0,
@@ -1774,7 +1721,7 @@
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
-            162
+            208
          ],
          "shape": 3,
          "slot_index": 0
@@ -1835,6 +1782,43 @@
        "1703665898041.png",
        "image"
      ]
+    },
+    {
+      "id": 129,
+      "type": "AppInfo",
+      "pos": [
+        4893,
+        -1778
+      ],
+      "size": {
+        "0": 400,
+        "1": 344.0000305175781
+      },
+      "flags": {},
+      "order": 16,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "LOGO",
+          "type": "IMAGE",
+          "link": 208
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AppInfo"
+      },
+      "widgets_values": [
+        "AIPC大赛模板",
+        "\n75\n118",
+        "57\n126\n127\n",
+        "投稿模板#发挥你的想象力",
+        4,
+        "#AIPC# 参赛作品",
+        "https://www.weibo.com",
+        "",
+        "enable",
+        1
+      ]
    }
  ],
  "links": [
@@ -2174,22 +2158,6 @@
      0,
      "IMAGE"
    ],
-    [
-      161,
-      98,
-      0,
-      101,
-      0,
-      "IMAGE"
-    ],
-    [
-      162,
-      106,
-      0,
-      98,
-      0,
-      "IMAGE"
-    ],
    [
      185,
      118,
@@ -2333,6 +2301,14 @@
      127,
      0,
      "IMAGE"
+    ],
+    [
+      208,
+      106,
+      0,
+      129,
+      0,
+      "IMAGE"
    ]
  ],
  "groups": [
@@ -2351,10 +2327,10 @@
    {
      "title": "Group",
      "bounding": [
-        4912,
+        4883,
        -2035,
-        637,
-        669
+        666,
+        611
      ],
      "color": "#444",
      "font_size": 24,
@@ -1,6 +1,6 @@
 {
-  "last_node_id": 22,
-  "last_link_id": 23,
+  "last_node_id": 23,
+  "last_link_id": 25,
  "nodes": [
    {
      "id": 9,
@@ -167,48 +167,6 @@
        "beautiful scenery nature glass bottle landscape, , purple galaxy bottle,"
      ]
    },
-    {
-      "id": 10,
-      "type": "VAEDecode",
-      "pos": [
-        2870,
-        630
-      ],
-      "size": {
-        "0": 210,
-        "1": 46
-      },
-      "flags": {
-        "collapsed": false
-      },
-      "order": 11,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "samples",
-          "type": "LATENT",
-          "link": 8
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": 9
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            12
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "VAEDecode"
-      }
-    },
    {
      "id": 16,
      "type": "ShowTextForGPT",
@@ -248,31 +206,6 @@
        "a girl face,super,(Pop Art:1.26),(Black and White:1.26)"
      ]
    },
-    {
-      "id": 11,
-      "type": "PreviewImage",
-      "pos": [
-        3319,
-        -161
-      ],
-      "size": {
-        "0": 435.8727111816406,
-        "1": 511.8609619140625
-      },
-      "flags": {},
-      "order": 13,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 13
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "PreviewImage"
-      }
-    },
    {
      "id": 5,
      "type": "KSampler",
@@ -349,7 +282,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 58
+        "1": 130
      },
      "flags": {},
      "order": 2,
@@ -370,7 +303,10 @@
        "Node name for S&R": "IntNumber"
      },
      "widgets_values": [
-        -1
+        0,
+        0,
+        1,
+        1
      ]
    },
    {
@@ -382,7 +318,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 82
+        "1": 106
      },
      "flags": {},
      "order": 3,
@@ -403,51 +339,7 @@
      },
      "widgets_values": [
        "Pop Art",
-        1.26
-      ]
-    },
-    {
-      "id": 12,
-      "type": "AppInfo",
-      "pos": [
-        2924,
-        846
-      ],
-      "size": {
-        "0": 400,
-        "1": 272
-      },
-      "flags": {},
-      "order": 12,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 12
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            13
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AppInfo"
-      },
-      "widgets_values": [
-        "Prompt-weight-test",
-        "21\n22\n18",
-        "11\n16",
-        "",
-        1,
-        "",
+        1.26,
        null
      ]
    },
@@ -460,7 +352,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 82
+        "1": 106
      },
      "flags": {},
      "order": 4,
@@ -481,7 +373,8 @@
      },
      "widgets_values": [
        "Black and White",
-        1.26
+        1.26,
+        null
      ]
    },
    {
@@ -584,6 +477,111 @@
        "disable",
        ""
      ]
+    },
+    {
+      "id": 11,
+      "type": "PreviewImage",
+      "pos": [
+        3449,
+        -102
+      ],
+      "size": {
+        "0": 435.8727111816406,
+        "1": 511.8609619140625
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 24
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      }
+    },
+    {
+      "id": 10,
+      "type": "VAEDecode",
+      "pos": [
+        2870,
+        630
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 8
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 9
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            24,
+            25
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 23,
+      "type": "AppInfo",
+      "pos": [
+        3363.0014990624995,
+        551.2261418945309
+      ],
+      "size": {
+        "0": 400,
+        "1": 344
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "LOGO",
+          "type": "IMAGE",
+          "link": 25
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AppInfo"
+      },
+      "widgets_values": [
+        "Prompt-weight-test",
+        "21\n22\n18",
+        "11\n16",
+        "",
+        1,
+        "",
+        "https://",
+        "",
+        "enable",
+        1
+      ]
    }
  ],
  "links": [
@@ -651,22 +649,6 @@
      1,
      "VAE"
    ],
-    [
-      12,
-      10,
-      0,
-      12,
-      0,
-      "IMAGE"
-    ],
-    [
-      13,
-      12,
-      0,
-      11,
-      0,
-      "IMAGE"
-    ],
    [
      16,
      15,
@@ -714,6 +696,22 @@
      13,
      1,
      "STRING"
+    ],
+    [
+      24,
+      10,
+      0,
+      11,
+      0,
+      "IMAGE"
+    ],
+    [
+      25,
+      10,
+      0,
+      23,
+      0,
+      "IMAGE"
    ]
  ],
  "groups": [],
@@ -1,6 +1,6 @@
 {
-  "last_node_id": 25,
-  "last_link_id": 32,
+  "last_node_id": 26,
+  "last_link_id": 34,
  "nodes": [
    {
      "id": 5,
@@ -41,48 +41,6 @@
        "text, watermark"
      ]
    },
-    {
-      "id": 6,
-      "type": "VAEDecode",
-      "pos": [
-        1867,
-        -2378
-      ],
-      "size": {
-        "0": 210,
-        "1": 46
-      },
-      "flags": {
-        "collapsed": false
-      },
-      "order": 10,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "samples",
-          "type": "LATENT",
-          "link": 7
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": 8
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            9
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "VAEDecode"
-      }
-    },
    {
      "id": 15,
      "type": "EnhanceImage",
@@ -101,7 +59,7 @@
        {
          "name": "image",
          "type": "IMAGE",
-          "link": 25
+          "link": 34
        }
      ],
      "outputs": [
@@ -122,57 +80,6 @@
        1.1
      ]
    },
-    {
-      "id": 21,
-      "type": "EmptyLatentImage",
-      "pos": [
-        998,
-        -2674
-      ],
-      "size": [
-        315,
-        106
-      ],
-      "flags": {},
-      "order": 8,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "width",
-          "type": "INT",
-          "link": 30,
-          "widget": {
-            "name": "width"
-          }
-        },
-        {
-          "name": "height",
-          "type": "INT",
-          "link": 32,
-          "widget": {
-            "name": "height"
-          }
-        }
-      ],
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "links": [
-            26
-          ],
-          "shape": 3
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "EmptyLatentImage"
-      },
-      "widgets_values": [
-        512,
-        512,
-        1
-      ]
-    },
    {
      "id": 24,
      "type": "LimitNumber",
@@ -262,7 +169,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 58
+        "1": 130
      },
      "flags": {},
      "order": 0,
@@ -283,7 +190,10 @@
        "Node name for S&R": "IntNumber"
      },
      "widgets_values": [
-        512
+        1,
+        0,
+        1,
+        1
      ]
    },
    {
@@ -295,7 +205,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 58
+        "1": 130
      },
      "flags": {},
      "order": 1,
@@ -316,7 +226,10 @@
        "Node name for S&R": "IntNumber"
      },
      "widgets_values": [
-        512
+        1,
+        0,
+        1,
+        1
      ]
    },
    {
@@ -428,7 +341,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        730250870715434,
+        52336089190516,
        "randomize",
        15,
        6.9,
@@ -437,39 +350,6 @@
        0.59
      ]
    },
-    {
-      "id": 14,
-      "type": "FloatSlider",
-      "pos": [
-        1007,
-        -2819
-      ],
-      "size": {
-        "0": 315,
-        "1": 58
-      },
-      "flags": {},
-      "order": 3,
-      "mode": 0,
-      "outputs": [
-        {
-          "name": "FLOAT",
-          "type": "FLOAT",
-          "links": [
-            16
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "title": "denoise",
-      "properties": {
-        "Node name for S&R": "FloatSlider"
-      },
-      "widgets_values": [
-        1
-      ]
-    },
    {
      "id": 16,
      "type": "PreviewImage",
@@ -535,24 +415,31 @@
      ]
    },
    {
-      "id": 7,
-      "type": "AppInfo",
+      "id": 6,
+      "type": "VAEDecode",
      "pos": [
-        2134,
-        -2528
+        1867,
+        -2378
      ],
      "size": {
-        "0": 408.4201965332031,
-        "1": 406.9195861816406
+        "0": 210,
+        "1": 46
      },
-      "flags": {},
-      "order": 11,
+      "flags": {
+        "collapsed": false
+      },
+      "order": 10,
      "mode": 0,
      "inputs": [
        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 9
+          "name": "samples",
+          "type": "LATENT",
+          "link": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 8
        }
      ],
      "outputs": [
@@ -560,12 +447,37 @@
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [
-            25
+            33,
+            34
          ],
-          "shape": 3,
          "slot_index": 0
        }
      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 26,
+      "type": "AppInfo",
+      "pos": [
+        2134,
+        -2264
+      ],
+      "size": {
+        "0": 400,
+        "1": 344.00006103515625
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "LOGO",
+          "type": "IMAGE",
+          "link": 33
+        }
+      ],
      "properties": {
        "Node name for S&R": "AppInfo"
      },
@@ -576,7 +488,97 @@
        "演示基本的文生图流程",
        1,
        "#comfyui-mixlab-nodes# ",
-        null
+        "https://",
+        "",
+        "enable",
+        1
+      ]
+    },
+    {
+      "id": 14,
+      "type": "FloatSlider",
+      "pos": [
+        1007,
+        -2860
+      ],
+      "size": {
+        "0": 315,
+        "1": 130
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "FLOAT",
+          "type": "FLOAT",
+          "links": [
+            16
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "title": "denoise",
+      "properties": {
+        "Node name for S&R": "FloatSlider"
+      },
+      "widgets_values": [
+        1,
+        0,
+        1,
+        0.001
+      ]
+    },
+    {
+      "id": 21,
+      "type": "EmptyLatentImage",
+      "pos": [
+        1004,
+        -2633
+      ],
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "link": 30,
+          "widget": {
+            "name": "width"
+          }
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "link": 32,
+          "widget": {
+            "name": "height"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            26
+          ],
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        512,
+        512,
+        1
      ]
    }
  ],
@@ -637,14 +639,6 @@
      1,
      "VAE"
    ],
-    [
-      9,
-      6,
-      0,
-      7,
-      0,
-      "IMAGE"
-    ],
    [
      16,
      14,
@@ -661,14 +655,6 @@
      0,
      "IMAGE"
    ],
-    [
-      25,
-      7,
-      0,
-      15,
-      0,
-      "IMAGE"
-    ],
    [
      26,
      21,
@@ -708,6 +694,22 @@
      21,
      1,
      "INT"
+    ],
+    [
+      33,
+      6,
+      0,
+      26,
+      0,
+      "IMAGE"
+    ],
+    [
+      34,
+      6,
+      0,
+      15,
+      0,
+      "IMAGE"
    ]
  ],
  "groups": [],
@@ -1,6 +1,6 @@
 {
-  "last_node_id": 133,
-  "last_link_id": 289,
+  "last_node_id": 134,
+  "last_link_id": 296,
  "nodes": [
    {
      "id": 42,
@@ -178,7 +178,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        487152733962296,
+        981322491518329,
        "randomize",
        13,
        8,
@@ -284,7 +284,7 @@
        {
          "name": "width",
          "type": "INT",
-          "link": 91,
+          "link": 291,
          "widget": {
            "name": "width"
          }
@@ -292,7 +292,7 @@
        {
          "name": "height",
          "type": "INT",
-          "link": 92,
+          "link": 292,
          "widget": {
            "name": "height"
          }
@@ -554,7 +554,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        1031291986804327,
+        836429510062488,
        "randomize",
        13,
        8,
@@ -824,7 +824,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        715240655341851,
+        24900528323969,
        "randomize",
        12,
        8,
@@ -875,67 +875,6 @@
        "Node name for S&R": "VAEDecode"
      }
    },
-    {
-      "id": 46,
-      "type": "NewLayer",
-      "pos": [
-        1012.7987748686522,
-        1330
-      ],
-      "size": {
-        "0": 315,
-        "1": 262
-      },
-      "flags": {},
-      "order": 32,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 78
-        },
-        {
-          "name": "mask",
-          "type": "MASK",
-          "link": 79
-        },
-        {
-          "name": "layers",
-          "type": "LAYER",
-          "link": 227,
-          "slot_index": 2
-        },
-        {
-          "name": "canvas",
-          "type": "IMAGE",
-          "link": null
-        }
-      ],
-      "outputs": [
-        {
-          "name": "layers",
-          "type": "LAYER",
-          "links": [
-            228
-          ],
-          "shape": 6,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "NewLayer"
-      },
-      "widgets_values": [
-        179,
-        134,
-        156,
-        146,
-        4,
-        "width",
-        ""
-      ]
-    },
    {
      "id": 65,
      "type": "NewLayer",
@@ -1221,42 +1160,6 @@
        ""
      ]
    },
-    {
-      "id": 28,
-      "type": "Reroute",
-      "pos": [
-        616,
-        1515
-      ],
-      "size": [
-        75,
-        26
-      ],
-      "flags": {},
-      "order": 13,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "",
-          "type": "*",
-          "link": 48
-        }
-      ],
-      "outputs": [
-        {
-          "name": "",
-          "type": "IMAGE",
-          "links": [
-            90
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "showOutputText": false,
-        "horizontal": false
-      }
-    },
    {
      "id": 96,
      "type": "Reroute",
@@ -1294,55 +1197,6 @@
        "horizontal": false
      }
    },
-    {
-      "id": 49,
-      "type": "GetImageSize",
-      "pos": [
-        999,
-        1189
-      ],
-      "size": {
-        "0": 210,
-        "1": 46
-      },
-      "flags": {},
-      "order": 24,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 90
-        }
-      ],
-      "outputs": [
-        {
-          "name": "width",
-          "type": "INT",
-          "links": [
-            91,
-            238,
-            248
-          ],
-          "shape": 3,
-          "slot_index": 0
-        },
-        {
-          "name": "height",
-          "type": "INT",
-          "links": [
-            92,
-            239,
-            249
-          ],
-          "shape": 3,
-          "slot_index": 1
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "GetImageSize"
-      }
-    },
    {
      "id": 118,
      "type": "NewLayer",
@@ -1376,7 +1230,7 @@
        {
          "name": "width",
          "type": "INT",
-          "link": 248,
+          "link": 295,
          "widget": {
            "name": "width"
          }
@@ -1384,7 +1238,7 @@
        {
          "name": "height",
          "type": "INT",
-          "link": 249,
+          "link": 296,
          "widget": {
            "name": "height"
          }
@@ -1572,7 +1426,7 @@
        {
          "name": "width",
          "type": "INT",
-          "link": 238,
+          "link": 293,
          "widget": {
            "name": "width"
          }
@@ -1580,7 +1434,7 @@
        {
          "name": "height",
          "type": "INT",
-          "link": 239,
+          "link": 294,
          "widget": {
            "name": "height"
          }
@@ -1955,7 +1809,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        397643785545040,
+        371831550273153,
        "randomize",
        13,
        8,
@@ -2164,7 +2018,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        590319162197911,
+        996820396025175,
        "randomize",
        13,
        8,
@@ -2310,7 +2164,7 @@
        "Node name for S&R": "KSampler"
      },
      "widgets_values": [
-        457217754867837,
+        763274893004397,
        "randomize",
        13,
        8,
@@ -2780,7 +2634,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 234
+        "1": 240
      },
      "flags": {},
      "order": 3,
@@ -2814,7 +2668,8 @@
        100,
        13,
        null,
-        true
+        true,
+        false
      ]
    },
    {
@@ -2986,10 +2841,10 @@
        100,
        706
      ],
-      "size": [
-        315,
-        234
-      ],
+      "size": {
+        "0": 315,
+        "1": 234
+      },
      "flags": {},
      "order": 15,
      "mode": 0,
@@ -3034,7 +2889,8 @@
        100,
        13,
        null,
-        true
+        true,
+        false
      ]
    },
    {
@@ -3044,10 +2900,10 @@
        100,
        1330
      ],
-      "size": [
-        315,
-        234
-      ],
+      "size": {
+        "0": 315,
+        "1": 234
+      },
      "flags": {},
      "order": 16,
      "mode": 0,
@@ -3091,7 +2947,8 @@
        100,
        13,
        null,
-        true
+        true,
+        false
      ]
    },
    {
@@ -3101,10 +2958,10 @@
        100,
        1922
      ],
-      "size": [
-        315,
-        234
-      ],
+      "size": {
+        "0": 315,
+        "1": 234
+      },
      "flags": {},
      "order": 17,
      "mode": 0,
@@ -3147,7 +3004,8 @@
        100,
        13,
        null,
-        true
+        true,
+        false
      ]
    },
    {
@@ -3159,7 +3017,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 70
+        "1": 174
      },
      "flags": {},
      "order": 6,
@@ -3175,13 +3033,37 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "r",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "g",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "b",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        },
+        {
+          "name": "a",
+          "type": "FLOAT",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
        "Node name for S&R": "Color"
      },
      "widgets_values": [
-        null,
+        "#000000",
        null
      ]
    },
@@ -3221,6 +3103,12 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
@@ -3263,6 +3151,12 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
@@ -3306,6 +3200,12 @@
          ],
          "shape": 3,
          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3
        }
      ],
      "properties": {
@@ -3334,6 +3234,152 @@
      ],
      "color": "#432",
      "bgcolor": "#653"
+    },
+    {
+      "id": 134,
+      "type": "GetImageSize_",
+      "pos": [
+        734,
+        1628
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 24,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 290
+        }
+      ],
+      "outputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "links": [
+            291,
+            293,
+            295
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": [
+            292,
+            294,
+            296
+          ],
+          "shape": 3,
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "GetImageSize_"
+      }
+    },
+    {
+      "id": 28,
+      "type": "Reroute",
+      "pos": [
+        597,
+        1627
+      ],
+      "size": [
+        75,
+        26
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "",
+          "type": "*",
+          "link": 48
+        }
+      ],
+      "outputs": [
+        {
+          "name": "",
+          "type": "IMAGE",
+          "links": [
+            290
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "showOutputText": false,
+        "horizontal": false
+      }
+    },
+    {
+      "id": 46,
+      "type": "NewLayer",
+      "pos": [
+        1056,
+        1247
+      ],
+      "size": {
+        "0": 315,
+        "1": 262
+      },
+      "flags": {},
+      "order": 32,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 78
+        },
+        {
+          "name": "mask",
+          "type": "MASK",
+          "link": 79
+        },
+        {
+          "name": "layers",
+          "type": "LAYER",
+          "link": 227,
+          "slot_index": 2
+        },
+        {
+          "name": "canvas",
+          "type": "IMAGE",
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "name": "layers",
+          "type": "LAYER",
+          "links": [
+            228
+          ],
+          "shape": 6,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "NewLayer"
+      },
+      "widgets_values": [
+        179,
+        134,
+        156,
+        146,
+        4,
+        "width",
+        ""
+      ]
    }
  ],
  "links": [
@@ -3433,30 +3479,6 @@
      1,
      "MASK"
    ],
-    [
-      90,
-      28,
-      0,
-      49,
-      0,
-      "IMAGE"
-    ],
-    [
-      91,
-      49,
-      0,
-      50,
-      0,
-      "INT"
-    ],
-    [
-      92,
-      49,
-      1,
-      50,
-      1,
-      "INT"
-    ],
    [
      111,
      63,
@@ -4001,22 +4023,6 @@
      0,
      "IMAGE"
    ],
-    [
-      238,
-      49,
-      0,
-      116,
-      3,
-      "INT"
-    ],
-    [
-      239,
-      49,
-      1,
-      116,
-      4,
-      "INT"
-    ],
    [
      247,
      116,
@@ -4025,22 +4031,6 @@
      2,
      "LAYER"
    ],
-    [
-      248,
-      49,
-      0,
-      118,
-      3,
-      "INT"
-    ],
-    [
-      249,
-      49,
-      1,
-      118,
-      4,
-      "INT"
-    ],
    [
      251,
      119,
@@ -4312,6 +4302,62 @@
      119,
      0,
      "IMAGE"
+    ],
+    [
+      290,
+      28,
+      0,
+      134,
+      0,
+      "IMAGE"
+    ],
+    [
+      291,
+      134,
+      0,
+      50,
+      0,
+      "INT"
+    ],
+    [
+      292,
+      134,
+      1,
+      50,
+      1,
+      "INT"
+    ],
+    [
+      293,
+      134,
+      0,
+      116,
+      3,
+      "INT"
+    ],
+    [
+      294,
+      134,
+      1,
+      116,
+      4,
+      "INT"
+    ],
+    [
+      295,
+      134,
+      0,
+      118,
+      3,
+      "INT"
+    ],
+    [
+      296,
+      134,
+      1,
+      118,
+      4,
+      "INT"
    ]
  ],
  "groups": [],
Author	SHA1	Message	Date
shadowcz007	812879610a	v0.14.0 发布新节点splitImage & gridoutput，用于分割图片和随机摆放元素修复若干bug	2024-01-20 21:43:18 +08:00
shadowcz007	c5e521ccc1	add splitImage&gridoutput	2024-01-20 17:39:53 +08:00
shadowcz007	bc1c8fa351	Update index.html	2024-01-19 09:45:03 +08:00
shadowcz007	7271fcf9c1	api	2024-01-18 22:49:13 +08:00
shadowcz007	ace3b7707b	Update README.md	2024-01-18 12:45:29 +08:00
shadowcz007	9eb65cc4ee	Update ClipInterrogator.py	2024-01-18 11:12:03 +08:00
shadowcz007	c5c2bc779c	add JoinWithDelimiter	2024-01-18 11:00:37 +08:00
shadowcz007	ae1751d9c0	Update Utils.py	2024-01-18 00:32:12 +08:00
shadowcz007	d17583ef7d	fixbug	2024-01-17 17:56:23 +08:00
shadowcz007	a363713ae0	v0.13.0 EmbeddingPrompt & 修复若干bug	2024-01-16 23:17:56 +08:00
shadowcz007	1566165bd4	Create space.txt	2024-01-16 17:50:51 +08:00
shadowcz007	fe065fa318	OutlineMask for inpaint	2024-01-16 10:54:26 +08:00
shadowcz007	202d5cf071	支持富文本定义跳转按钮	2024-01-15 14:21:39 +08:00
shadowcz007	b785a9dc5b	add EmbeddingPrompt	2024-01-15 13:02:26 +08:00
shadowcz007	73bc658b2f	修复 sentencepiece 未安装的bug	2024-01-15 08:40:07 +08:00
shadowcz007	0b94216138	Update ui_mixlab.js	2024-01-14 20:35:27 +08:00
shadowcz007	86eec2b4cc	Update ui_mixlab.js	2024-01-14 20:34:07 +08:00
shadowcz007	c99b531d28	Update ui_mixlab.js	2024-01-14 20:33:53 +08:00
shadowcz007	74a4338cb5	Merge branch 'main' of https://github.com/shadowcz007/comfyui-mixlab-nodes	2024-01-14 13:14:42 +08:00
shadowcz007	d691c52e49	Update TextGenerateNode.py	2024-01-14 13:12:10 +08:00
gold3bear	bd3e9e4b3c	去掉调试数据	2024-01-14 12:31:05 +08:00
shadow	3c3ca5fb9c	Merge pull request #138 from shadowcz007/fix-chinese-prompt Fix chinese prompt	2024-01-14 11:58:08 +08:00
shadowcz007	e4ff4fce1c	update	2024-01-14 11:57:18 +08:00
gold3bear	2918d4b07d	correct Chinese text to prompt syntax	2024-01-14 11:50:14 +08:00
gold3bear	c40e49be46	fix chinese prompt	2024-01-14 11:34:58 +08:00
shadowcz007	4ccda20975	add rembg	2024-01-14 11:06:46 +08:00
shadowcz007	09957617d3	修复SwitchByIndex的bug	2024-01-13 20:59:29 +08:00
shadowcz007	c703aa7058	中文prompt增加选项，可控制是否添加更多	2024-01-13 20:59:07 +08:00
shadowcz007	64d366d323	Update prompt_mixlab.js	2024-01-13 17:12:03 +08:00
shadowcz007	333e0a2faa	Update ImageNode.py	2024-01-13 16:32:51 +08:00
shadowcz007	a677d95bc8	Update README.md	2024-01-13 16:02:24 +08:00
shadowcz007	aafd87e84b	v0.12.0 ChinesePrompt && PromptGenerate > ChinesePrompt && PromptGenerate，中文prompt节点，直接用中文书写你的prompt ![](./assets/ChinesePrompt_workflow.svg) > Web App增加图片编辑器	2024-01-13 15:59:52 +08:00
shadowcz007	efa3bae54b	Create profession.txt	2024-01-13 12:25:05 +08:00
shadowcz007	8e4362689d	Lama、ClipInterrogator安装移到节点内	2024-01-13 12:11:46 +08:00
shadowcz007	b86634284e	appinfo运行bug	2024-01-13 11:34:17 +08:00
shadowcz007	b3293ddccd	优化promptImage的预览	2024-01-12 17:16:47 +08:00
shadowcz007	4b40831b83	prompt keywords	2024-01-11 23:05:25 +08:00
shadowcz007	e426b0521c	添加图片编辑功能	2024-01-11 23:01:58 +08:00
shadowcz007	1777bf6e06	修复切换workflow，数据未清空的情况	2024-01-11 23:01:42 +08:00
shadowcz007	dafc892f0f	add image edit for web app	2024-01-11 15:41:05 +08:00
shadowcz007	fea0cfd5dd	更新workflow示例	2024-01-11 15:40:31 +08:00
shadowcz007	a7e158db6d	update workflow example	2024-01-11 15:32:20 +08:00
shadowcz007	455ac4abd3	Update promptslide-appinfo-workflow.svg	2024-01-11 15:27:11 +08:00
shadowcz007	778dfa2cf5	update workflow example	2024-01-11 15:24:31 +08:00
shadowcz007	329f2e6f81	系统字体的获取	2024-01-10 16:19:49 +08:00
shadowcz007	63ad6d97d7	Update ImageNode.py	2024-01-09 22:59:34 +08:00
shadowcz007	8db56db7cf	Update ImageNode.py	2024-01-09 22:34:13 +08:00
shadowcz007	bd542f1e0b	Update app_mixlab.js	2024-01-09 18:42:36 +08:00
shadowcz007	a162e53dea	Update ImageNode.py	2024-01-09 18:05:18 +08:00
shadowcz007	a8a4c848ed	Update __init__.py	2024-01-09 16:15:15 +08:00
shadowcz007	bddd38996a	Update ImageNode.py	2024-01-09 15:16:38 +08:00
shadowcz007	9f084eae94	修复LoadImagesFromPath的bug	2024-01-09 14:33:13 +08:00
shadowcz007	c54c635161	v0.11.4	2024-01-09 12:59:36 +08:00
shadowcz007	fa8b42e05e	增强ImageCrop功能	2024-01-09 12:48:20 +08:00
shadowcz007	9c3c323884	fixbug: user_manager	2024-01-09 12:41:29 +08:00
shadowcz007	c8a46439be	v0.11.3 - 修复appinfo的logo输入	2024-01-09 09:17:00 +08:00
shadowcz007	b7ec701259	Update Utils.py	2024-01-09 09:16:15 +08:00
shadowcz007	a2cd0e0a38	v0.11.2 - 优化appinfo - 自动保存 - 优化mergeLayer，可以输出合成的mask - 添加一个实验性的节点 ImageColorTransfer - random prompt ,增加上传关键词功能 - 修复LoadImageFromPath的bug	2024-01-08 23:03:37 +08:00
shadowcz007	7bccc0e236	优化appinfo-不需要输出，每次运行都会自动更新数据	2024-01-08 23:01:31 +08:00
shadowcz007	a3a649a79f	修复 LoadImagesFromPath 不更新的bug	2024-01-08 22:11:10 +08:00
shadowcz007	2a14d30552	添加一个实验性的节点 ImageColorTransfer	2024-01-08 16:40:00 +08:00
shadowcz007	313bef0609	ClipInterrogator优化	2024-01-07 22:55:24 +08:00
shadowcz007	960a80aeca	Merge branch 'main' of https://github.com/shadowcz007/comfyui-mixlab-nodes	2024-01-07 19:59:24 +08:00
shadowcz007	20e6d50a98	修复bug	2024-01-07 19:59:22 +08:00
shadow	507c3417d6	Merge pull request #114 from shadowcz007/fix_ssl_prot_occupied fix:ssl prot occupied	2024-01-07 17:08:08 +08:00