app.py

import gradio as gr
import numpy as np
import random
import torch
import spaces
import cv2
import face_recognition
from diffusers import DiffusionPipeline, StableDiffusionImg2ImgPipeline
from PIL import Image
from transformers import CLIPTextModel, CLIPTokenizer

# Configuración del dispositivo y tipo de datos
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

# Cargar los pipelines para las diferentes tareas
pipe_diffusion = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)
pipe_img2img = StableDiffusionImg2ImgPipeline.from_pretrained("runwayml/stable-diffusion-v1-5").to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048

# Configurar tokenizer y modelo CLIP para truncar correctamente los prompts
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
text_model = CLIPTextModel.from_pretrained("openai/clip-vit-base-patch32")

def truncate_prompt(prompt, max_length=77):
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"][0][:max_length]
    truncated_prompt = tokenizer.decode(input_ids, skip_special_tokens=True)
    return truncated_prompt

def swap_faces(source_image, target_image):
    source_face = face_recognition.face_locations(source_image)[0]
    target_face = face_recognition.face_locations(target_image)[0]

    target_face_image = target_image[target_face[0]:target_face[2], target_face[3]:target_face[1]]
    source_face_image = source_image[source_face[0]:source_face[2], source_face[3]:source_face[1]]

    target_face_resized = cv2.resize(target_face_image, (source_face_image.shape[1], source_face_image.shape[0]))

    mask = np.zeros_like(source_face_image)
    cv2.fillConvexPoly(mask, np.array(list(face_recognition.face_landmarks(target_image, [target_face])[0].values())), (255, 255, 255))

    swapped_face = cv2.seamlessClone(target_face_resized, source_image, mask, (source_face[3] + source_face_image.shape[1]//2, source_face[0] + source_face_image.shape[0]//2), cv2.NORMAL_CLONE)
    
    return swapped_face

@spaces.GPU()
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, init_image=None, reference_image=None, img2img_strength=0.75, progress=gr.Progress(track_tqdm=True)):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator().manual_seed(seed)
    
    # Truncar el prompt si es demasiado largo
    prompt = truncate_prompt(prompt)
    
    # Convertir init_image a formato PIL si no lo está
    if init_image and not isinstance(init_image, Image.Image):
        init_image = Image.fromarray(np.array(init_image))

    # Generación de la imagen
    if init_image:
        init_image = init_image.convert("RGB")
        generated_image = pipe_img2img(
            prompt=prompt, 
            init_image=init_image,
            strength=img2img_strength,
            num_inference_steps=num_inference_steps,
            generator=generator
        ).images[0]
    else:
        generated_image = pipe_diffusion(
            prompt=prompt, 
            width=width,
            height=height,
            num_inference_steps=num_inference_steps, 
            generator=generator,
            guidance_scale=0.0
        ).images[0]
    
    # Aplicación de Face Swap
    if reference_image:
        reference_image = np.array(reference_image)
        generated_image = np.array(generated_image)
        generated_image = swap_faces(generated_image, reference_image)
        generated_image = Image.fromarray(generated_image)
    
    return generated_image, seed

examples = [
    "a tiny astronaut hatching from an egg on the moon",
    "a cat holding a sign that says hello world",
    "an anime illustration of a wiener schnitzel",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""# FLUX.1 [schnell] + Stable Diffusion img2img + Face Swap
Combinación de generación de imágenes, transformación de imágenes con img2img, y Face Swap.
        """)
        
        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)
        
        with gr.Accordion("Advanced Settings", open=False):
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )
            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
            width = gr.Slider(
                label="Width",
                minimum=256,
                maximum=MAX_IMAGE_SIZE,
                step=32,
                value=1024,
            )
            height = gr.Slider(
                label="Height",
                minimum=256,
                maximum=MAX_IMAGE_SIZE,
                step=32,
                value=1024,
            )
            num_inference_steps = gr.Slider(
                label="Number of inference steps",
                minimum=1,
                maximum=50,
                step=1,
                value=4,
            )
            init_image = gr.Image(type="pil", label="Imagen Inicial (opcional)")
            img2img_strength = gr.Slider(
                label="Img2Img Strength",
                minimum=0.0,
                maximum=1.0,
                step=0.05,
                value=0.75,
            )
            reference_image = gr.Image(type="pil", label="Imagen de Referencia (opcional)")

        gr.Examples(
            examples=examples,
            fn=infer,
            inputs=[prompt],
            outputs=[result, seed],
            cache_examples="lazy"
        )

        gr.on(
            triggers=[run_button.click, prompt.submit],
            fn=infer,
            inputs=[prompt, seed, randomize_seed, width, height, num_inference_steps, init_image, reference_image, img2img_strength],
            outputs=[result, seed]
        )

demo.launch()