Partly SDXL working

Api call

install.py

@@ -1,20 +1,55 @@
 import os
 import subprocess
-from huggingface_hub import snapshot_download
+from huggingface_hub import snapshot_download, hf_hub_download
 parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 models_dir = os.path.abspath(os.path.join(parent_dir, '..', "models"))
 print(models_dir)
 
-# Download the model from the Hugging Face Hub
-repo_id = "LiuZichen/MagicQuill-models"  # or any other model/dataset ID
-snapshot_download(repo_id=repo_id, local_dir=models_dir)
+
+hugging_face_repos = [
+    {
+        'repo_id': 'LiuZichen/MagicQuill-models',
+        'local_dir': models_dir
+    },
+
+    # SDXL
+    {
+        'repo_id': 'xinsir/controlnet-scribble-sdxl-1.0',
+        'local_dir': os.path.join(models_dir, 'controlnet', 'SDXL'),
+        'filename': 'diffusion_pytorch_model.safetensors',
+        'target_filename': 'sdxl-controlnet-scribble-1.0.safetensors'
+    },
+    {
+        'repo_id': 'briaai/BRIA-2.3-ControlNet-ColorGrid',
+        'local_dir': os.path.join(models_dir, 'controlnet', 'SDXL'),
+        'filename': 'bria_23_controlnet_colorgrid.safetensors',
+        'target_filename': 'bria_23_controlnet_colorgrid.safetensors'
+    },
+    {
+        'repo_id': 'fullnonstop/random_mask_brushnet_ckpt_sdxl_v0',
+        'local_dir': os.path.join(models_dir, 'inpaint', 'SDXL'),
+        'filename': 'random_mask_brushnet_ckpt_sdxl_v0.safetensors',
+        'target_filename': 'random_mask_brushnet_ckpt_sdxl_v0.safetensors'
+    }
+]
+
+for repo in hugging_face_repos:
+    if 'filename' in repo:
+       filename = hf_hub_download(repo_id=repo['repo_id'], local_dir=repo['local_dir'], filename=repo['filename'])
+       current_path = os.path.join(repo['local_dir'], filename)
+       target_path = os.path.join(repo['local_dir'], repo['target_filename'])
+       if os.path.exists(current_path):
+         if current_path != target_path:
+             os.rename(current_path, target_path)
+    else:
+        snapshot_download(repo_id=repo['repo_id'], local_dir=repo['local_dir'])
 
 repos = {
     'ComfyUI_BrushNet': 'https://github.com/nullquant/ComfyUI-BrushNet',
     'comfyui_controlnet_aux': 'https://github.com/Fannovel16/comfyui_controlnet_aux'
 }
 
-# for name, url in repos.items():
-#     target_dir = os.path.join(parent_dir, name)
-#     if not os.path.exists(target_dir):
-#         subprocess.run(['git', 'clone', url, target_dir], check=True)
+for name, url in repos.items():
+    target_dir = os.path.join(parent_dir, name)
+    if not os.path.exists(target_dir):
+        subprocess.run(['git', 'clone', url, target_dir], check=True)

magic_quill.py

@@ -1,6 +1,7 @@
 import hashlib
 import os
 import json
+import random
 from server import PromptServer
 from PIL import Image, ImageOps
 import torch
@@ -9,12 +10,20 @@ import folder_paths
 from aiohttp import web
 import io
 import base64
+import time
 
 import comfy.samplers
 from .scribble_color_edit import ScribbleColorEditModel
 from .llava_new import LLaVAModel
+import torch.nn.functional as F
 
 def tensor_to_base64(tensor):
+    if isinstance(tensor, dict) and "samples" in tensor:
+        # Handle dictionary with 'samples' key (latent)
+        # For latent, we'll just return an empty string since latents aren't viewable directly
+        return ""  # or implement specific handling for latent samples
+    
+    # For tensor input, process normally
     tensor = tensor.squeeze(0) * 255.
     pil_image = Image.fromarray(tensor.cpu().byte().numpy())
     buffered = io.BytesIO()
@@ -81,25 +90,276 @@ async def process_background_img(request):
 @PromptServer.instance.routes.post("/magic_quill/guess_prompt")
 async def guess_prompt_handler(request):
     json_data = await request.json()
-    add_color_image = json_data.get("add_color_image", None)
-    original_image = json_data.get("original_image", None)
-    add_edge_image = json_data.get("add_edge_image", None)
+    add_color_image_data = json_data.get("add_color_image", None)
+    original_image_data = json_data.get("original_image", None)
+    add_edge_image_data = json_data.get("add_edge_image", None)
 
-    original_image_path = folder_paths.get_annotated_filepath(original_image)
-    original_image_tensor = load_and_preprocess_image(original_image_path)
-    
-    if add_color_image:
-        add_color_image_path = folder_paths.get_annotated_filepath(add_color_image)
-        add_color_image_tensor = load_and_preprocess_image(add_color_image_path)
-    else:
-        add_color_image_tensor = original_image_tensor
-    
-    width, height = original_image_tensor.shape[1], original_image_tensor.shape[2]
-    add_edge_mask = create_alpha_mask(folder_paths.get_annotated_filepath(add_edge_image)) if add_edge_image else torch.zeros((1, height, width), dtype=torch.float32, device="cpu")
+    if not original_image_data:
+        return web.json_response({"error": "Original image is required."}, status=400)
 
-    res = MagicQuill.guess_prompt(original_image_tensor, add_color_image_tensor, add_edge_mask)
+    temp_files_to_clean = []
+    input_dir = folder_paths.get_input_directory()
+
+    def is_base64(s):
+        return isinstance(s, str) and s.startswith("data:image/")
+
+    def handle_image_input(image_data, filename_base):
+        if is_base64(image_data):
+            try:
+                image = read_base64_image(image_data)
+                timestamp = int(time.time())
+                # Use a short hash to minimize collision chance but keep filename reasonable
+                hash_part = hashlib.sha1(str(timestamp).encode() + image_data.encode()).hexdigest()[:8]
+                filename = f"{filename_base}_{timestamp}_{hash_part}.png"
+                filepath = os.path.join(input_dir, filename)
+                image.save(filepath)
+                print(f"Saved temporary image to {filepath}")
+                temp_files_to_clean.append(filepath)
+                return filepath
+            except Exception as e:
+                print(f"Error processing base64 image for {filename_base}: {e}")
+                # Raise or return error? For now, let it raise to signal failure.
+                raise ValueError(f"Invalid base64 data for {filename_base}") from e
+        elif isinstance(image_data, str): # Assume filename
+            return folder_paths.get_annotated_filepath(image_data)
+        else: # Handle None or other invalid types
+            return None
+
+    try:
+        original_image_path = handle_image_input(original_image_data, "guess_original")
+        if not original_image_path or not os.path.exists(original_image_path):
+             return web.json_response({"error": f"Original image not found or invalid: {original_image_data}"}, status=400)
+             
+        original_image_tensor = load_and_preprocess_image(original_image_path)
+        
+        add_color_image_path = None
+        if add_color_image_data:
+            add_color_image_path = handle_image_input(add_color_image_data, "guess_add_color")
+            if not add_color_image_path or not os.path.exists(add_color_image_path):
+                print(f"Warning: Add color image specified but not found or invalid: {add_color_image_data}. Using original image.")
+                add_color_image_path = None # Fallback
+
+        if add_color_image_path:
+            add_color_image_tensor = load_and_preprocess_image(add_color_image_path)
+        else:
+            add_color_image_tensor = original_image_tensor # Fallback to original
+        
+        add_edge_image_path = None
+        if add_edge_image_data:
+            add_edge_image_path = handle_image_input(add_edge_image_data, "guess_add_edge")
+            if not add_edge_image_path or not os.path.exists(add_edge_image_path):
+                 print(f"Warning: Add edge image specified but not found or invalid: {add_edge_image_data}. Ignoring add edge.")
+                 add_edge_image_path = None # Ignore if invalid
+
+        width, height = original_image_tensor.shape[2], original_image_tensor.shape[1] # Corrected order W, H
+        add_edge_mask = create_alpha_mask(add_edge_image_path) if add_edge_image_path else torch.zeros((1, height, width), dtype=torch.float32, device="cpu")
+
+        # Ensure mask dimensions match original image
+        if add_edge_mask.shape[1] != height or add_edge_mask.shape[2] != width:
+             add_edge_mask = F.interpolate(add_edge_mask.unsqueeze(0), size=(height, width), mode='nearest').squeeze(0)
+
+        res = MagicQuill.guess_prompt(original_image_tensor, add_color_image_tensor, add_edge_mask)
+
+        return web.json_response({"prompt": res, "error": False})
+
+    except Exception as e:
+        import traceback
+        traceback_str = traceback.format_exc()
+        print(f"Error in guess_prompt_handler: {str(e)}\nTraceback: {traceback_str}")
+        return web.json_response({"error": str(e), "traceback": traceback_str}, status=500)
+    finally:
+        # Cleanup temporary files
+        for filepath in temp_files_to_clean:
+            try:
+                if os.path.exists(filepath):
+                    os.remove(filepath)
+                    print(f"Cleaned up temporary file: {filepath}")
+            except Exception as e:
+                print(f"Warning: Error cleaning up temporary file {filepath}: {str(e)}")
+
+@PromptServer.instance.routes.post("/magic_quill/run")
+async def run_magic_quill(request):
+    try:
+        post = await request.json()
+        base64_image = post.get("image")
+        if not base64_image:
+            return web.json_response({"error": "No image provided"}, status=400)
+
+        # Generate a unique prompt ID for this request
+        prompt_id = str(hashlib.sha256(str(time.time()).encode()).hexdigest()[:8])
+        PromptServer.instance.last_prompt_id = prompt_id
+        PromptServer.instance.last_node_id = "magic_quill"
+        
+        # Get the input directory path
+        input_dir = folder_paths.get_input_directory()
+        
+        # Generate unique filenames for this request
+        timestamp = int(time.time())
+        if post.get("dynamic_filenames", False):
+            main_image_filename = f"api_image_{timestamp}.png"
+            original_image_filename = f"api_original_{timestamp}.png"
+            add_color_image_filename = f"api_add_color_{timestamp}.png"
+            add_edge_image_filename = f"api_add_edge_{timestamp}.png"
+            remove_edge_image_filename = f"api_remove_edge_{timestamp}.png"
+        else:
+            main_image_filename = f"clipspace-mask-MagicQuill_-1.png"
+            original_image_filename = f"original_MagicQuill_-1.png"
+            add_color_image_filename = f"add_color_MagicQuill_-1.png"
+            add_edge_image_filename = f"add_edge_MagicQuill_-1.png"
+            remove_edge_image_filename = f"remove_edge_MagicQuill_-1.png"   
+        
+        # Save main image
+        main_image_path = os.path.join(input_dir, main_image_filename)
+        image = read_base64_image(base64_image)
+        image.save(main_image_path)
+        print(f"Saved main image to {main_image_path}")
+        
+        # Save original image if provided, otherwise use main image
+        base64_original = post.get("original_image")
+        if base64_original:
+            original_image_path = os.path.join(input_dir, original_image_filename)
+            original_image = read_base64_image(base64_original)
+            original_image.save(original_image_path)
+            original_image_file = original_image_filename
+        else:
+            original_image_file = main_image_filename
+        
+        # Process and save optional images if provided
+        add_color_image_file = None
+        add_edge_image_file = None
+        remove_edge_image_file = None
+        
+        # Save add_color_image if provided
+        base64_add_color = post.get("add_color_image")
+        if base64_add_color:
+            add_color_image_path = os.path.join(input_dir, add_color_image_filename)
+            add_color_image = read_base64_image(base64_add_color)
+            add_color_image.save(add_color_image_path)
+            add_color_image_file = add_color_image_filename
+            
+        # Save add_edge_image if provided
+        base64_add_edge = post.get("add_edge_image")
+        if base64_add_edge:
+            add_edge_image_path = os.path.join(input_dir, add_edge_image_filename)
+            add_edge_image = read_base64_image(base64_add_edge)
+            add_edge_image.save(add_edge_image_path)
+            add_edge_image_file = add_edge_image_filename
+            
+        # Save remove_edge_image if provided
+        base64_remove_edge = post.get("remove_edge_image")
+        if base64_remove_edge:
+            remove_edge_image_path = os.path.join(input_dir, remove_edge_image_filename)
+            remove_edge_image = read_base64_image(base64_remove_edge)
+            remove_edge_image.save(remove_edge_image_path)
+            remove_edge_image_file = remove_edge_image_filename
+        
+        # Get other parameters from the request
+        checkpoint_name = post.get("checkpoint_name", "SD1.5/DreamShaper.safetensors")
+        ckpt_path = folder_paths.get_full_path_or_raise("checkpoints", checkpoint_name)
+        out = comfy.sd.load_checkpoint_guess_config(ckpt_path)
+        
+        model = out[0]
+        clip = out[1]
+        vae = out[2]
+        
+        random_seed = random.randint(0, 0xffffffffffffffff)
+        
+        if not model or not vae or not clip:
+            return web.json_response({"error": "Missing required model objects"}, status=400)
+            
+        base_model_version = post.get("base_model_version", "SD1.5")
+        positive_prompt = post.get("positive_prompt", "")
+        negative_prompt = post.get("negative_prompt", "")
+        dtype = post.get("dtype", "float16")
+        grow_size = post.get("grow_size", 15)
+        stroke_as_edge = post.get("stroke_as_edge", "enable")
+        fine_edge = post.get("fine_edge", "disable")
+        edge_strength = post.get("edge_strength", 0.5)
+        color_strength = post.get("color_strength", 0.5)
+        inpaint_strength = post.get("inpaint_strength", 1.0)
+        
+        seed = post.get("seed", random_seed) #Random seed
+        steps = post.get("steps", 20)
+        cfg = post.get("cfg", 4.0)
+        sampler_name = post.get("sampler_name", "euler_ancestral")
+        scheduler = post.get("scheduler", "exponential")
+
+
+        if "SDXL" in checkpoint_name:
+            base_model_version = "SDXL"
+        elif "SD1.5" in checkpoint_name:
+            base_model_version = "SD1.5"
+        else:
+            raise ValueError(f"Could not determine base model version from checkpoint name: {checkpoint_name} use base_model_version parameter")
+
+        print(f"Using files - Main: {main_image_filename}, Original: {original_image_file}, Add Color: {add_color_image_file}, Add Edge: {add_edge_image_file}, Remove Edge: {remove_edge_image_file}")
+
+        # Call painter_execute with file paths instead of tensors
+        result = MagicQuill.painter_execute(
+            image=main_image_filename,
+            original_image=original_image_file,
+            add_color_image=add_color_image_file,
+            add_edge_image=add_edge_image_file,
+            remove_edge_image=remove_edge_image_file,
+            model=model,
+            vae=vae,
+            clip=clip,
+            base_model_version=base_model_version,
+            positive_prompt=positive_prompt,
+            negative_prompt=negative_prompt,
+            dtype=dtype,
+            grow_size=grow_size,
+            stroke_as_edge=stroke_as_edge,
+            fine_edge=fine_edge,
+            edge_strength=edge_strength,
+            color_strength=color_strength,
+            inpaint_strength=inpaint_strength,
+            seed=seed,
+            steps=steps,
+            cfg=cfg,
+            sampler_name=sampler_name,
+            scheduler=scheduler
+        )
+
+        # Convert the result tensors to base64
+        latent, image, edge_map, color_palette = result
+        
+        # Send progress update
+        PromptServer.instance.send_sync(
+            "progress", {"value": 1, "max": 1, "prompt_id": prompt_id, "node": "magic_quill"}
+        )
+        
+        # Clean up temporary files (optional)
+        if post.get("cleanup", False):
+            try:
+                if os.path.exists(main_image_path):
+                    os.remove(main_image_path)
+                if base64_original and os.path.exists(os.path.join(input_dir, original_image_filename)):
+                    os.remove(os.path.join(input_dir, original_image_filename))
+                if base64_add_color and os.path.exists(os.path.join(input_dir, add_color_image_filename)):
+                    os.remove(os.path.join(input_dir, add_color_image_filename))
+                if base64_add_edge and os.path.exists(os.path.join(input_dir, add_edge_image_filename)):
+                    os.remove(os.path.join(input_dir, add_edge_image_filename))
+                if base64_remove_edge and os.path.exists(os.path.join(input_dir, remove_edge_image_filename)):
+                    os.remove(os.path.join(input_dir, remove_edge_image_filename))
+            except Exception as e:
+                print(f"Warning: Error cleaning up temporary files: {str(e)}")
+        
+        return web.json_response({
+            "status": "success",
+            "result": {
+                "latent": tensor_to_base64(latent),
+                "image": tensor_to_base64(image),
+                "edge_map": tensor_to_base64(edge_map),
+                "color_palette": tensor_to_base64(color_palette)
+            }
+        })
+    except Exception as e:
+        import traceback
+        traceback_str = traceback.format_exc()
+        print(f"Error: {str(e)}\nTraceback: {traceback_str}")
+        return web.json_response({"error": str(e), "traceback": traceback_str}, status=500)
 
-    return web.json_response({"prompt": res, "error": False})
 
 class MagicQuill(object):
     scribbleColorEditModel = ScribbleColorEditModel()
@@ -128,7 +388,7 @@ class MagicQuill(object):
                 "clip": ("CLIP",),
                 "vae": ("VAE",),
                 
-                "base_model_version": (['SD1.5'], {"default": "SD1.5"}),
+                "base_model_version": (['SD1.5', 'SDXL'], {"default": "SD1.5"}),
                 "positive_prompt": ("STRING", {"default": ""}),
                 "negative_prompt": ("STRING", {"default": ""}),
                 "dtype": (['float16', 'bfloat16', 'float32', 'float64'], {"default": "float16"}),
@@ -159,11 +419,10 @@ class MagicQuill(object):
 
     @classmethod
     def prepare_images_and_masks(cls, image, original_image, add_color_image, add_edge_image, remove_edge_image):
+        # Handle file path inputs
         image_path = folder_paths.get_annotated_filepath(image)
         image_tensor = load_and_preprocess_image(image_path)
-        
-        width, height = image_tensor.shape[1], image_tensor.shape[2]
-        
+        height, width = image_tensor.shape[1], image_tensor.shape[2]
         total_mask = create_alpha_mask(image_path)
         
         original_image_path = folder_paths.get_annotated_filepath(original_image)
@@ -175,11 +434,21 @@ class MagicQuill(object):
         else:
             add_color_image_tensor = original_image_tensor
         
-        add_edge_mask = create_alpha_mask(folder_paths.get_annotated_filepath(add_edge_image)) if add_edge_image else torch.zeros_like(total_mask)
+        add_edge_mask = create_alpha_mask(folder_paths.get_annotated_filepath(add_edge_image)) if add_edge_image else torch.zeros((1, height, width), dtype=torch.float32, device="cpu")
+        remove_edge_mask = create_alpha_mask(folder_paths.get_annotated_filepath(remove_edge_image)) if remove_edge_image else torch.zeros((1, height, width), dtype=torch.float32, device="cpu")
         
-        remove_edge_mask = create_alpha_mask(folder_paths.get_annotated_filepath(remove_edge_image)) if remove_edge_image else torch.zeros_like(total_mask)
+        # Ensure all tensors have correct dimensions
+        if add_edge_mask.shape[1] != height or add_edge_mask.shape[2] != width:
+            add_edge_mask = F.interpolate(add_edge_mask.unsqueeze(0), size=(height, width), mode='nearest').squeeze(0)
+            
+        if remove_edge_mask.shape[1] != height or remove_edge_mask.shape[2] != width:
+            remove_edge_mask = F.interpolate(remove_edge_mask.unsqueeze(0), size=(height, width), mode='nearest').squeeze(0)
+            
+        if total_mask.shape[1] != height or total_mask.shape[2] != width:
+            total_mask = F.interpolate(total_mask.unsqueeze(0), size=(height, width), mode='nearest').squeeze(0)
         
-        return add_color_image_tensor, original_image_tensor, total_mask, add_edge_mask, remove_edge_mask
+        # Ensure all tensor operations detach gradients
+        return add_color_image_tensor.detach(), original_image_tensor.detach(), total_mask.detach(), add_edge_mask.detach(), remove_edge_mask.detach()
 
     @classmethod
     def guess_prompt(cls, original_image_tensor, add_color_image_tensor, add_edge_mask):
@@ -194,7 +463,8 @@ class MagicQuill(object):
 
     @classmethod
     def painter_execute(cls, image, original_image, add_color_image, add_edge_image, remove_edge_image, model, vae, clip, base_model_version, positive_prompt, negative_prompt, dtype, grow_size, stroke_as_edge, fine_edge, edge_strength, color_strength, inpaint_strength, seed, steps, cfg, sampler_name, scheduler):
-        print(image, original_image, add_color_image, add_edge_image, remove_edge_image, model, vae, clip, base_model_version, positive_prompt, negative_prompt, dtype, grow_size, edge_strength, color_strength, inpaint_strength, seed, steps, cfg, sampler_name, scheduler)
+        print(f"model: {model} vae: {vae} clip: {clip} base_model_version: {base_model_version} positive_prompt: {positive_prompt} negative_prompt: {negative_prompt} dtype: {dtype} grow_size: {grow_size} stroke_as_edge: {stroke_as_edge} fine_edge: {fine_edge} edge_strength: {edge_strength} color_strength: {color_strength} inpaint_strength: {inpaint_strength} seed: {seed} steps: {steps} cfg: {cfg} sampler_name: {sampler_name} scheduler: {scheduler}")
+        print(f"original_image: {original_image} add_color_image: {add_color_image} add_edge_image: {add_edge_image} remove_edge_image: {remove_edge_image}")
         add_color_image, original_image, total_mask, add_edge_mask, remove_edge_mask = cls.prepare_images_and_masks(image, original_image, add_color_image, add_edge_image, remove_edge_image)
 
         if torch.sum(remove_edge_mask).item() > 0 and torch.sum(add_edge_mask).item() == 0:
@@ -208,9 +478,18 @@ class MagicQuill(object):
         print("positive prompt: ", positive_prompt)
         latent_samples, final_image, lineart_output, color_output = cls.scribbleColorEditModel.process(model, vae, clip, original_image, add_color_image, base_model_version, positive_prompt, negative_prompt, dtype, total_mask, add_edge_mask, remove_edge_mask, grow_size, stroke_as_edge, fine_edge, edge_strength, color_strength, inpaint_strength, seed, steps, cfg, sampler_name, scheduler)
 
+        # Ensure all data is serializable before sending via JSON
+        # Convert tensor to base64 string
         final_image_base64 = tensor_to_base64(final_image)
+        
+        # Get the string representation of the image path if it's not a tensor
+        image_name = image
+        if isinstance(image, torch.Tensor):
+            image_name = "generated_image"
+            
+        # Send the serializable data
         PromptServer.instance.send_sync(
-            "magic_quill/final_image", {"image": final_image_base64, "image_name": image}
+            "magic_quill/final_image", {"image": final_image_base64, "image_name": image_name}
         )
         
         return (latent_samples, final_image, lineart_output, color_output)

requirements.txt

@@ -1,4 +1,3 @@
-webcolors==1.13
 opencv-python
 diffusers
 torchsde==0.2.6
@@ -20,7 +19,7 @@ fastapi
 einops==0.6.1
 einops-exts==0.0.4
 timm==0.6.13
-
+webcolors==24.11.1
 torch
 importlib_metadata
 huggingface_hub

scribble_color_edit.py

@@ -2,6 +2,8 @@ import os
 import torch.nn.functional as F
 import torch
 import sys
+import torch.utils._pytree as pytree
+import numpy as np
 
 current_dir = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(current_dir)
@@ -38,14 +40,46 @@ class ScribbleColorEditModel():
             edge_controlnet_name = "control_v11p_sd15_scribble.safetensors"
             color_controlnet_name = "color_finetune.safetensors"
             brushnet_name = os.path.join("brushnet", "random_mask_brushnet_ckpt", "diffusion_pytorch_model.safetensors")
+        elif base_model_version == "SDXL":
+            edge_controlnet_name = "SDXL/sdxl-controlnet-scribble-1.0.safetensors"
+            color_controlnet_name = "SDXL/bria_23_controlnet_colorgrid.safetensors"
+            brushnet_name = os.path.join("SDXL", "random_mask_brushnet_ckpt_sdxl_v0.safetensors")
         else:
             raise ValueError("Invalid base_model_version, not supported yet!!!: {}".format(base_model_version))
+        print(f"Loading edge controlnet: {edge_controlnet_name} color controlnet: {color_controlnet_name} brushnet: {brushnet_name}")
+        
         self.edge_controlnet = self.controlnet_loader.load_controlnet(edge_controlnet_name)[0]
         self.color_controlnet = self.controlnet_loader.load_controlnet(color_controlnet_name)[0]
         self.brushnet_loader.inpaint_files = get_files_with_extension('inpaint')
         print("self.brushnet_loader.inpaint_files: ", get_files_with_extension('inpaint'))
         self.brushnet = self.brushnet_loader.brushnet_loading(brushnet_name, dtype)[0]
 
+    def safe_vae_decode(self, vae, latent_samples):
+        """Safe VAE decoding that handles inference tensors correctly."""
+        # First, ensure the latent samples are on CPU and detached
+        samples = latent_samples["samples"].to(device="cpu").detach().clone()
+        
+        # Convert to standard float format
+        samples = samples.float()
+        
+        # Disable gradient tracking for this operation
+        with torch.no_grad():
+            # Create a fresh dictionary with the cloned tensor
+            latent_dict = {"samples": samples}
+            try:
+                # Decode using the VAE
+                return self.vae_decoder.decode(vae, latent_dict)
+            except RuntimeError as e:
+                # If we still encounter an error, try a deeper copy approach
+                print(f"First VAE decode attempt failed: {str(e)}")
+                
+                # Create completely fresh tensors by serializing and deserializing
+                serialized = pytree.tree_map(lambda x: x.detach().cpu().numpy() if isinstance(x, torch.Tensor) else x, latent_dict)
+                deserialized = pytree.tree_map(lambda x: torch.tensor(x) if isinstance(x, np.ndarray) else x, serialized)
+                
+                # Try decoding again with the completely new tensors
+                return self.vae_decoder.decode(vae, deserialized)
+
     def process(self, model, vae, clip, image, colored_image, base_model_version, positive_prompt, negative_prompt, dtype, mask, add_mask, remove_mask, grow_size, stroke_as_edge, fine_edge, edge_strength, color_strength, inpaint_strength, seed, steps, cfg, sampler_name, scheduler):
         print("mask.shape", mask.shape)
         print("image.shape", image.shape)
@@ -115,8 +149,47 @@ class ScribbleColorEditModel():
             latent_image=latent,
         )[0]
 
-        final_image = self.vae_decoder.decode(vae, latent_samples)[0]
-        final_image = self.blender.blend_inpaint(final_image, image, mask, kernel=10, sigma=10.0)[0]
-
+        # Use the safe VAE decode method instead of direct decoding
+        final_image = self.safe_vae_decode(vae, latent_samples)[0]
+        
+        # Ensure image dimensions match before blending (handle RGB vs RGBA)
+        if final_image.shape[-1] != image.shape[-1]:
+            print(f"Dimension mismatch: final_image shape: {final_image.shape}, image shape: {image.shape}")
+            
+            # Handle different dimensions properly
+            # First, make sure we understand the tensor shapes
+            print(f"final_image.dim() = {final_image.dim()}, image.dim() = {image.dim()}")
+            
+            # Convert both to 3D (H,W,C) format if they're not already
+            if final_image.dim() == 4:
+                final_image = final_image.squeeze(0)  # Remove batch dimension if present
+            if image.dim() == 4:
+                image = image.squeeze(0)  # Remove batch dimension if present
+                
+            # Now handle channel differences
+            if final_image.shape[-1] == 3 and image.shape[-1] == 4:
+                # Add an alpha channel (fully opaque) to final_image
+                alpha_channel = torch.ones((final_image.shape[0], final_image.shape[1], 1), 
+                                          device=final_image.device, dtype=final_image.dtype)
+                final_image = torch.cat([final_image, alpha_channel], dim=-1)
+            elif final_image.shape[-1] == 4 and image.shape[-1] == 3:
+                # Use only RGB channels from final_image or add alpha to image
+                final_image = final_image[..., :3]
+            else:
+                # Just use the first 3 channels for both
+                final_image = final_image[..., :3]
+                if image.shape[-1] > 3:
+                    image = image[..., :3]
+        
+        # Print shape information before blending
+        print(f"Before blending - final_image shape: {final_image.shape}, image shape: {image.shape}, mask shape: {mask.shape}")
+        
+        # Make sure mask has the right dimensions for blending
+        if mask.dim() == 3 and mask.shape[0] == 1:  # If mask is [1, H, W]
+            mask_for_blend = mask.squeeze(0)        # Convert to [H, W]
+        else:
+            mask_for_blend = mask
+            
+        final_image = self.blender.blend_inpaint(final_image, image, mask_for_blend, kernel=10, sigma=10.0)[0]
 
         return (latent_samples, final_image, lineart_output, color_output)

utils.py

@@ -34,8 +34,8 @@ def get_colored_contour(img1, img2, threshold=10):
 
 def closest_colour(requested_colour):
     min_colours = {}
-    for key, name in webcolors.CSS3_HEX_TO_NAMES.items():
-        r_c, g_c, b_c = webcolors.hex_to_rgb(key)
+    for name in webcolors.names("css3"):
+        r_c, g_c, b_c = webcolors.name_to_rgb(name)
         rd = (r_c - requested_colour[0].item()) ** 2
         gd = (g_c - requested_colour[1].item()) ** 2
         bd = (b_c - requested_colour[2].item()) ** 2