comfy_pulid.py

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)