import torch import spaces from diffusers import DDIMScheduler, StableDiffusionXLPipeline import ipown from huggingface_hub import hf_hub_download from insightface.app import FaceAnalysis import gradio as gr import cv2 # List of models for switching model_options = { "CyberRealistic": "John6666/cyberrealistic-pony-v61-sdxl", "StallionDreams": "John6666/stallion-dreams-pony-realistic-v1-sdxl", "PonyRealism": "John6666/pony-realism-v21main-sdxl" } # Full style list for applying styles to the prompt style_list = [ { "name": "(No style)", "prompt": "{prompt}", "negative_prompt": "longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality", }, { "name": "Cinematic", "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured", }, { "name": "3D Model", "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting", "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting", }, { "name": "Anime", "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime, highly detailed", "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast", }, { "name": "Digital Art", "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed", "negative_prompt": "photo, photorealistic, realism, ugly", }, { "name": "Photographic", "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed", "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly", }, { "name": "Pixel art", "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics", "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic", }, { "name": "Fantasy art", "prompt": "ethereal fantasy concept art of {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy", "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white", }, { "name": "Neonpunk", "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional", "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured", }, { "name": "Manga", "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style", "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style", }, ] # Styles dictionary to map style names to prompts and negative prompts styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list} STYLE_NAMES = list(styles.keys()) DEFAULT_STYLE_NAME = "(No style)" # Function to apply the selected style def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]: p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME]) return p.replace("{prompt}", positive), n + negative # Download the necessary model component ip_ckpt = hf_hub_download(repo_id="h94/IP-Adapter-FaceID", filename="ip-adapter-faceid_sdxl.bin", repo_type="model") device = "cuda" # Configure the noise scheduler noise_scheduler = DDIMScheduler( num_train_timesteps=1000, beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False, steps_offset=1, ) # Function to initialize the pipeline with a selected model def get_pipeline(model_path): return StableDiffusionXLPipeline.from_pretrained( model_path, torch_dtype=torch.float16, scheduler=noise_scheduler, use_safetensors=True, ) # Initialize with a default model current_model = model_options["PonyRealism"] pipe = get_pipeline(current_model) ip_model = ipown.IPAdapterFaceIDXL(pipe, ip_ckpt, device) @spaces.GPU() def generate_image(images, model_choice, style_name, prompt, negative_prompt, face_strength, likeness_strength, num_inference_steps, guidance_scale, width, height): global current_model, pipe, ip_model # Update the model if the choice has changed if model_options[model_choice] != current_model: current_model = model_options[model_choice] pipe = get_pipeline(current_model) ip_model = ipown.IPAdapterFaceIDXL(pipe, ip_ckpt, device) torch.cuda.empty_cache() app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider']) app.prepare(ctx_id=0, det_size=(512, 512)) faceid_all_embeds = [] for image in images: face = cv2.imread(image) faces = app.get(face) faceid_embed = torch.from_numpy(faces[0].normed_embedding).unsqueeze(0) faceid_all_embeds.append(faceid_embed) average_embedding = torch.mean(torch.stack(faceid_all_embeds, dim=0), dim=0) # Apply the selected style styled_prompt, styled_negative_prompt = apply_style(style_name, prompt, negative_prompt) image = ip_model.generate( prompt=styled_prompt, negative_prompt=styled_negative_prompt, faceid_embeds=average_embedding, scale=likeness_strength, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps ) return image def swap_to_gallery(images): return gr.update(value=images, visible=True), gr.update(visible=True), gr.update(visible=False) def remove_back_to_files(): return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True) css = ''' h1{margin-bottom: 0 !important} ''' with gr.Blocks(css=css) as demo: gr.Markdown("# IP-Adapter-FaceID SDXL demo") gr.Markdown("A simple Demo for the [h94/IP-Adapter-FaceID SDXL model](https://huggingface.co/h94/IP-Adapter-FaceID).") with gr.Row(): with gr.Column(): model_dropdown = gr.Dropdown(label="Select Model", choices=list(model_options.keys()), value="PonyRealism") style_dropdown = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME) files = gr.Files(label="Drag 1 or more photos of your face", file_types=["image"]) uploaded_files = gr.Gallery(label="Your images", visible=False, columns=5, rows=1, height=250) with gr.Column(visible=False) as clear_button: remove_and_reupload = gr.ClearButton(value="Remove files and upload new ones", components=files, size="sm") prompt = gr.Textbox(label="Prompt", placeholder="A photo of a man/woman/person ...") negative_prompt = gr.Textbox(label="Negative Prompt", placeholder="low quality") face_strength = gr.Slider(label="Face Strength", value=7.5, step=0.1, minimum=0, maximum=15) likeness_strength = gr.Slider(label="Likeness Strength", value=1.0, step=0.1, minimum=0, maximum=5) with gr.Accordion("Advanced Options", open=False): num_inference_steps = gr.Slider(label="Number of Inference Steps", value=30, step=1, minimum=10, maximum=100) guidance_scale = gr.Slider(label="Guidance Scale", value=7.5, step=0.1, minimum=1, maximum=20) width = gr.Slider(label="Width", value=512, step=64, minimum=256, maximum=1024) height = gr.Slider(label="Height", value=512, step=64, minimum=256, maximum=1024) submit = gr.Button("Submit", variant="primary") with gr.Column(): gallery = gr.Gallery(label="Generated Images") files.upload(fn=swap_to_gallery, inputs=files, outputs=[uploaded_files, clear_button, files]) remove_and_reupload.click(fn=remove_back_to_files, outputs=[uploaded_files, clear_button, files]) submit.click(fn=generate_image, inputs=[files, model_dropdown, style_dropdown, prompt, negative_prompt, face_strength, likeness_strength, num_inference_steps, guidance_scale, width, height], outputs=gallery) demo.launch()