import os import random import sys from typing import Sequence, Mapping, Any, Union import torch from comfy import model_management from huggingface_hub import hf_hub_download import spaces hf_hub_download(repo_id="black-forest-labs/FLUX.1-Redux-dev", filename="flux1-redux-dev.safetensors", local_dir="models/style_models") hf_hub_download(repo_id="black-forest-labs/FLUX.1-Depth-dev", filename="flux1-depth-dev.safetensors", local_dir="models/diffusion_models") hf_hub_download(repo_id="Comfy-Org/sigclip_vision_384", filename="sigclip_vision_patch14_384.safetensors", local_dir="models/clip_vision") hf_hub_download(repo_id="Kijai/DepthAnythingV2-safetensors", filename="depth_anything_v2_vitl_fp32.safetensors", local_dir="models/depthanything") hf_hub_download(repo_id="black-forest-labs/FLUX.1-dev", filename="ae.safetensors", local_dir="models/vae/FLUX1") hf_hub_download(repo_id="comfyanonymous/flux_text_encoders", filename="clip_l.safetensors", local_dir="models/text_encoders") hf_hub_download(repo_id="comfyanonymous/flux_text_encoders", filename="t5xxl_fp16.safetensors", local_dir="models/text_encoders/t5") def get_value_at_index(obj: Union[Sequence, Mapping], index: int) -> Any: """Returns the value at the given index of a sequence or mapping. If the object is a sequence (like list or string), returns the value at the given index. If the object is a mapping (like a dictionary), returns the value at the index-th key. Some return a dictionary, in these cases, we look for the "results" key Args: obj (Union[Sequence, Mapping]): The object to retrieve the value from. index (int): The index of the value to retrieve. Returns: Any: The value at the given index. Raises: IndexError: If the index is out of bounds for the object and the object is not a mapping. """ try: return obj[index] except KeyError: return obj["result"][index] def find_path(name: str, path: str = None) -> str: """ Recursively looks at parent folders starting from the given path until it finds the given name. Returns the path as a Path object if found, or None otherwise. """ # If no path is given, use the current working directory if path is None: path = os.getcwd() # Check if the current directory contains the name if name in os.listdir(path): path_name = os.path.join(path, name) print(f"{name} found: {path_name}") return path_name # Get the parent directory parent_directory = os.path.dirname(path) # If the parent directory is the same as the current directory, we've reached the root and stop the search if parent_directory == path: return None # Recursively call the function with the parent directory return find_path(name, parent_directory) def add_comfyui_directory_to_sys_path() -> None: """ Add 'ComfyUI' to the sys.path """ comfyui_path = find_path("ComfyUI") if comfyui_path is not None and os.path.isdir(comfyui_path): sys.path.append(comfyui_path) print(f"'{comfyui_path}' added to sys.path") def add_extra_model_paths() -> None: """ Parse the optional extra_model_paths.yaml file and add the parsed paths to the sys.path. """ try: from main import load_extra_path_config except ImportError: print( "Could not import load_extra_path_config from main.py. Looking in utils.extra_config instead." ) from utils.extra_config import load_extra_path_config extra_model_paths = find_path("extra_model_paths.yaml") if extra_model_paths is not None: load_extra_path_config(extra_model_paths) else: print("Could not find the extra_model_paths config file.") add_comfyui_directory_to_sys_path() add_extra_model_paths() def import_custom_nodes() -> None: """Find all custom nodes in the custom_nodes folder and add those node objects to NODE_CLASS_MAPPINGS This function sets up a new asyncio event loop, initializes the PromptServer, creates a PromptQueue, and initializes the custom nodes. """ import asyncio import execution from nodes import init_extra_nodes import server # Creating a new event loop and setting it as the default loop loop = asyncio.new_event_loop() asyncio.set_event_loop(loop) # Creating an instance of PromptServer with the loop server_instance = server.PromptServer(loop) execution.PromptQueue(server_instance) # Initializing custom nodes init_extra_nodes() from nodes import NODE_CLASS_MAPPINGS intconstant = NODE_CLASS_MAPPINGS["INTConstant"]() dualcliploader = NODE_CLASS_MAPPINGS["DualCLIPLoader"]() #To be added to `model_loaders` as it loads a model dualcliploader_357 = dualcliploader.load_clip( clip_name1="t5/t5xxl_fp16.safetensors", clip_name2="clip_l.safetensors", type="flux", ) cr_clip_input_switch = NODE_CLASS_MAPPINGS["CR Clip Input Switch"]() cliptextencode = NODE_CLASS_MAPPINGS["CLIPTextEncode"]() loadimage = NODE_CLASS_MAPPINGS["LoadImage"]() imageresize = NODE_CLASS_MAPPINGS["ImageResize+"]() getimagesizeandcount = NODE_CLASS_MAPPINGS["GetImageSizeAndCount"]() vaeloader = NODE_CLASS_MAPPINGS["VAELoader"]() #To be added to `model_loaders` as it loads a model vaeloader_359 = vaeloader.load_vae(vae_name="FLUX1/ae.safetensors") vaeencode = NODE_CLASS_MAPPINGS["VAEEncode"]() unetloader = NODE_CLASS_MAPPINGS["UNETLoader"]() #To be added to `model_loaders` as it loads a model unetloader_358 = unetloader.load_unet( unet_name="flux1-depth-dev.safetensors", weight_dtype="default" ) ksamplerselect = NODE_CLASS_MAPPINGS["KSamplerSelect"]() randomnoise = NODE_CLASS_MAPPINGS["RandomNoise"]() fluxguidance = NODE_CLASS_MAPPINGS["FluxGuidance"]() depthanything_v2 = NODE_CLASS_MAPPINGS["DepthAnything_V2"]() downloadandloaddepthanythingv2model = NODE_CLASS_MAPPINGS[ "DownloadAndLoadDepthAnythingV2Model" ]() #To be added to `model_loaders` as it loads a model downloadandloaddepthanythingv2model_437 = ( downloadandloaddepthanythingv2model.loadmodel( model="depth_anything_v2_vitl_fp32.safetensors" ) ) instructpixtopixconditioning = NODE_CLASS_MAPPINGS[ "InstructPixToPixConditioning" ]() text_multiline_454 = text_multiline.text_multiline(text="FLUX_Redux") clipvisionloader = NODE_CLASS_MAPPINGS["CLIPVisionLoader"]() #To be added to `model_loaders` as it loads a model clipvisionloader_438 = clipvisionloader.load_clip( clip_name="sigclip_vision_patch14_384.safetensors" ) clipvisionencode = NODE_CLASS_MAPPINGS["CLIPVisionEncode"]() stylemodelloader = NODE_CLASS_MAPPINGS["StyleModelLoader"]() #To be added to `model_loaders` as it loads a model stylemodelloader_441 = stylemodelloader.load_style_model( style_model_name="flux1-redux-dev.safetensors" ) text_multiline = NODE_CLASS_MAPPINGS["Text Multiline"]() emptylatentimage = NODE_CLASS_MAPPINGS["EmptyLatentImage"]() cr_conditioning_input_switch = NODE_CLASS_MAPPINGS[ "CR Conditioning Input Switch" ]() cr_model_input_switch = NODE_CLASS_MAPPINGS["CR Model Input Switch"]() stylemodelapplyadvanced = NODE_CLASS_MAPPINGS["StyleModelApplyAdvanced"]() basicguider = NODE_CLASS_MAPPINGS["BasicGuider"]() basicscheduler = NODE_CLASS_MAPPINGS["BasicScheduler"]() samplercustomadvanced = NODE_CLASS_MAPPINGS["SamplerCustomAdvanced"]() vaedecode = NODE_CLASS_MAPPINGS["VAEDecode"]() saveimage = NODE_CLASS_MAPPINGS["SaveImage"]() imagecrop = NODE_CLASS_MAPPINGS["ImageCrop+"]() #Add all the models that load a safetensors file model_loaders = [dualcliploader_357, vaeloader_359, unetloader_358, clipvisionloader_438, stylemodelloader_441, downloadandloaddepthanythingv2model_437] # Check which models are valid and how to best load them valid_models = [ getattr(loader[0], 'patcher', loader[0]) for loader in model_loaders if not isinstance(loader[0], dict) and not isinstance(getattr(loader[0], 'patcher', None), dict) ] #Finally loads the models model_management.load_models_gpu(valid_models) def generate_image(prompt, structure_image, style_image, depth_strength, style_strength): import_custom_nodes() with torch.inference_mode(): dualcliploader = NODE_CLASS_MAPPINGS["DualCLIPLoader"]() dualcliploader_11 = dualcliploader.load_clip( clip_name1="clip_l.safetensors", clip_name2="t5xxl_fp8_e4m3fn.safetensors", type="flux", ) loadimage = NODE_CLASS_MAPPINGS["LoadImage"]() loadimage_97 = loadimage.load_image(image=structure_image) pulidfluxinsightfaceloader = NODE_CLASS_MAPPINGS["PulidFluxInsightFaceLoader"]() pulidfluxinsightfaceloader_98 = pulidfluxinsightfaceloader.load_insightface( provider="CUDA" ) pulidfluxmodelloader = NODE_CLASS_MAPPINGS["PulidFluxModelLoader"]() pulidfluxmodelloader_99 = pulidfluxmodelloader.load_model( pulid_file="pulid_flux_v0.9.1.safetensors" ) pulidfluxevacliploader = NODE_CLASS_MAPPINGS["PulidFluxEvaClipLoader"]() pulidfluxevacliploader_100 = pulidfluxevacliploader.load_eva_clip() cliptextencode = NODE_CLASS_MAPPINGS["CLIPTextEncode"]() cliptextencode_121 = cliptextencode.encode( text=prompt, clip=get_value_at_index(dualcliploader_11, 0) ) conditioningzeroout = NODE_CLASS_MAPPINGS["ConditioningZeroOut"]() conditioningzeroout_116 = conditioningzeroout.zero_out( conditioning=get_value_at_index(cliptextencode_121, 0) ) loadimage_129 = loadimage.load_image( image=style_image ) getimagesize = NODE_CLASS_MAPPINGS["GetImageSize+"]() getimagesize_113 = getimagesize.execute( image=get_value_at_index(loadimage_129, 0) ) imageresize = NODE_CLASS_MAPPINGS["ImageResize+"]() imageresize_112 = imageresize.execute( width=get_value_at_index(getimagesize_113, 0), height=get_value_at_index(getimagesize_113, 1), interpolation="nearest", method="keep proportion", condition="always", multiple_of=0, image=get_value_at_index(loadimage_129, 0), ) layermask_personmaskultra = NODE_CLASS_MAPPINGS["LayerMask: PersonMaskUltra"]() layermask_personmaskultra_120 = layermask_personmaskultra.person_mask_ultra( face=True, hair=False, body=False, clothes=False, accessories=False, background=False, confidence=0.4, detail_range=16, black_point=0.01, white_point=0.99, process_detail=True, images=get_value_at_index(imageresize_112, 0), ) growmask = NODE_CLASS_MAPPINGS["GrowMask"]() growmask_118 = growmask.expand_mask( expand=43, tapered_corners=True, mask=get_value_at_index(layermask_personmaskultra_120, 1), ) maskblur = NODE_CLASS_MAPPINGS["MaskBlur+"]() maskblur_119 = maskblur.execute( amount=60, device="auto", mask=get_value_at_index(growmask_118, 0) ) inpaintmodelconditioning = NODE_CLASS_MAPPINGS["InpaintModelConditioning"]() inpaintmodelconditioning_110 = inpaintmodelconditioning.encode( noise_mask=True, positive=get_value_at_index(cliptextencode_121, 0), negative=get_value_at_index(conditioningzeroout_116, 0), vae=get_value_at_index(vaeloader_10, 0), pixels=get_value_at_index(imageresize_112, 0), mask=get_value_at_index(maskblur_119, 0), ) unetloader = NODE_CLASS_MAPPINGS["UNETLoader"]() unetloader_111 = unetloader.load_unet( unet_name="FLUX1/flux1-dev.safetensors", weight_dtype="fp8_e4m3fn" ) randomnoise = NODE_CLASS_MAPPINGS["RandomNoise"]() randomnoise_114 = randomnoise.get_noise(noise_seed=random.randint(1, 2**64)) ksamplerselect = NODE_CLASS_MAPPINGS["KSamplerSelect"]() ksamplerselect_115 = ksamplerselect.get_sampler(sampler_name="euler") applypulidflux = NODE_CLASS_MAPPINGS["ApplyPulidFlux"]() repeatlatentbatch = NODE_CLASS_MAPPINGS["RepeatLatentBatch"]() basicguider = NODE_CLASS_MAPPINGS["BasicGuider"]() basicscheduler = NODE_CLASS_MAPPINGS["BasicScheduler"]() samplercustomadvanced = NODE_CLASS_MAPPINGS["SamplerCustomAdvanced"]() vaedecode = NODE_CLASS_MAPPINGS["VAEDecode"]() saveimage = NODE_CLASS_MAPPINGS["SaveImage"]() applypulidflux_101 = applypulidflux.apply_pulid_flux( weight=1.1, start_at=0, end_at=1, fusion="max", fusion_weight_max=1, fusion_weight_min=0, train_step=1000, use_gray=True, model=get_value_at_index(unetloader_111, 0), pulid_flux=get_value_at_index(pulidfluxmodelloader_99, 0), eva_clip=get_value_at_index(pulidfluxevacliploader_100, 0), face_analysis=get_value_at_index(pulidfluxinsightfaceloader_98, 0), image=get_value_at_index(loadimage_97, 0), unique_id=12000670301720322250, ) repeatlatentbatch_107 = repeatlatentbatch.repeat( amount=1, samples=get_value_at_index(inpaintmodelconditioning_110, 2) ) basicguider_117 = basicguider.get_guider( model=get_value_at_index(applypulidflux_101, 0), conditioning=get_value_at_index(inpaintmodelconditioning_110, 0), ) basicscheduler_130 = basicscheduler.get_sigmas( scheduler="normal", steps=14, denoise=0.6, model=get_value_at_index(unetloader_111, 0), ) samplercustomadvanced_109 = samplercustomadvanced.sample( noise=get_value_at_index(randomnoise_114, 0), guider=get_value_at_index(basicguider_117, 0), sampler=get_value_at_index(ksamplerselect_115, 0), sigmas=get_value_at_index(basicscheduler_130, 0), latent_image=get_value_at_index(repeatlatentbatch_107, 0), ) vaedecode_122 = vaedecode.decode( samples=get_value_at_index(samplercustomadvanced_109, 0), vae=get_value_at_index(vaeloader_10, 0), ) saveimage_127 = saveimage.save_images( filename_prefix="ComfyUI", images=get_value_at_index(vaedecode_122, 0) ) saved_path = f"output/{saveimage_127['ui']['images'][0]['filename']}" return saved_path if __name__ == "__main__": with gr.Blocks() as app: # Add a title gr.Markdown("# FLUX Style Shaping") with gr.Row(): with gr.Column(): # Add an input prompt_input = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...") # Add a `Row` to include the groups side by side with gr.Row(): # First group includes structure image and depth strength with gr.Group(): structure_image = gr.Image(label="Structure Image", type="filepath") depth_strength = gr.Slider(minimum=0, maximum=50, value=15, label="Depth Strength") # Second group includes style image and style strength with gr.Group(): style_image = gr.Image(label="Style Image", type="filepath") style_strength = gr.Slider(minimum=0, maximum=1, value=0.5, label="Style Strength") # The generate button generate_btn = gr.Button("Generate") with gr.Column(): # The output image output_image = gr.Image(label="Generated Image") # When clicking the button, it will trigger the `generate_image` function, with the respective inputs # and the output an image generate_btn.click( fn=generate_image, inputs=[prompt_input, structure_image, style_image, depth_strength, style_strength], outputs=[output_image] ) app.launch(share=True)