app.py

mport gradio as gr
import numpy as np
import torch
from diffusers import StableDiffusionPipeline
from peft import PeftModel, LoraConfig
import os

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_default = "stable-diffusion-v1-5/stable-diffusion-v1-5"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

def get_lora_sd_pipeline(
    lora_dir='./lora_man_animestyle',
    base_model_name_or_path=None, 
    dtype=torch.float16, 
    adapter_name="default"
    ):

    unet_sub_dir = os.path.join(lora_dir, "unet")
    text_encoder_sub_dir = os.path.join(lora_dir, "text_encoder")
    
    if os.path.exists(text_encoder_sub_dir) and base_model_name_or_path is None:
        config = LoraConfig.from_pretrained(text_encoder_sub_dir)
        base_model_name_or_path = config.base_model_name_or_path
    
    if base_model_name_or_path is None:
        raise ValueError("Укажите название базовой модели или путь к ней")
    
    pipe = StableDiffusionPipeline.from_pretrained(base_model_name_or_path, torch_dtype=dtype)
    before_params = pipe.unet.parameters()
    pipe.unet = PeftModel.from_pretrained(pipe.unet, unet_sub_dir, adapter_name=adapter_name)
    pipe.unet.set_adapter(adapter_name)
    after_params = pipe.unet.parameters()
    
    if os.path.exists(text_encoder_sub_dir):
        pipe.text_encoder = PeftModel.from_pretrained(pipe.text_encoder, text_encoder_sub_dir, adapter_name=adapter_name)
    
    if dtype in (torch.float16, torch.bfloat16):
        pipe.unet.half()
        pipe.text_encoder.half()
    
    return pipe

def long_prompt_encoder(prompt, tokenizer, text_encoder, max_length=77):
    tokens = tokenizer(prompt, truncation=False, return_tensors="pt")["input_ids"]
    part_s = [tokens[:, i:i + max_length] for i in range(0, tokens.shape[1], max_length)]
    with torch.no_grad():
        embeds = [text_encoder(part.to(text_encoder.device))[0] for part in part_s]
    return torch.cat(embeds, dim=1)

def align_embeddings(prompt_embeds, negative_prompt_embeds):
    max_length = max(prompt_embeds.shape[1], negative_prompt_embeds.shape[1])
    return torch.nn.functional.pad(prompt_embeds, (0, 0, 0, max_length - prompt_embeds.shape[1])), \
           torch.nn.functional.pad(negative_prompt_embeds, (0, 0, 0, max_length - negative_prompt_embeds.shape[1]))

pipe_default = get_lora_sd_pipeline(lora_dir='./lora_man_animestyle', base_model_name_or_path=model_default, dtype=torch_dtype).to(device)

def infer(
    prompt, 
    negative_prompt, 
    width=512, 
    height=512, 
    num_inference_steps=20, 
    model='stable-diffusion-v1-5/stable-diffusion-v1-5', 
    seed=4, 
    guidance_scale=7.5, 
    lora_scale=0.5,
    use_control_net=False,  # Добавляем параметр для управления включением ControlNet
    control_net_weight=1.0,  # Вес ControlNet, если он включен
    progress=gr.Progress(track_tqdm=True)
    ):
    
    generator = torch.Generator(device).manual_seed(seed)
    
    if model != model_default:
        pipe = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype).to(device)
        prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
        negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
        prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
    else:
        pipe = pipe_default
        prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
        negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
        prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
        pipe.fuse_lora(lora_scale=lora_scale) # Коэфф. добавления lora
    
    params = {
        'prompt_embeds': prompt_embeds,
        'negative_prompt_embeds': negative_prompt_embeds,
        'guidance_scale': guidance_scale,
        'num_inference_steps': num_inference_steps,
        'width': width,
        'height': height,
        'generator': generator,
    }
    
    if use_control_net:  # Если ControlNet включен
        params['control_net'] = True  # Включаем использование ControlNet
        params['control_net_weight'] = control_net_weight  # Устанавливаем вес ControlNet
    
    return pipe(**params).images[0]

examples = [
    "A young man in anime style. The image is characterized by high definition and resolution. Handsome, thoughtful man, attentive eyes. The man is depicted in the foreground, close-up or in the middle. High-quality images of the face, eyes, nose, lips, hands, fingers and clothes. The background and background are blurred and indistinct. The play of light and shadow is visible on the face and clothes.",
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k.",
    "An astronaut riding a green horse.",
]    

examples_negative = [
    "blurred details, low resolution, poor image of a man's face, poor quality, artifacts, black and white image",
    "blurry details, low resolution, poorly defined edges",
    "bad face, bad quality, artifacts, low-res, black and white",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

available_models = [
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    "SG161222/Realistic_Vision_V3.0_VAE",
    "CompVis/stable-diffusion-v1-4",
    "stabilityai/sdxl-turbo",
    "runwayml/stable-diffusion-v1-5",
    "sd-legacy/stable-diffusion-v1-5",
    "prompthero/openjourney",
    "stabilityai/stable-diffusion-3-medium-diffusers",
    "stabilityai/stable-diffusion-3.5-large",
    "stabilityai/stable-diffusion-3.5-large-turbo",
]

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image Gradio Template from V. Gorsky")

        with gr.Row():
            model = gr.Dropdown(
                label="Model Selection",
                choices=available_models,
                value="stable-diffusion-v1-5/stable-diffusion-v1-5",
                interactive=True
            )
        
        prompt = gr.Textbox(
            label="Prompt",
            max_lines=1,
            placeholder="Enter your prompt",
        )

        negative_prompt = gr.Textbox(
            label="Negative prompt",
            max_lines=1,
            placeholder="Enter a negative prompt",
        )

        with gr.Row():
            lora_scale = gr.Slider(
                label="LoRA scale",
                minimum=0.0,
                maximum=1.0,
                step=0.05,
                value=0.5,
            ) 

        with gr.Row():
            guidance_scale = gr.Slider(
                label="Guidance scale",
                minimum=0.0,
                maximum=10.0,
                step=0.1,
                value=7.5,
            )  
        
        with gr.Row():
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=4,
            )

        with gr.Row():
            num_inference_steps = gr.Slider(
                label="Number of inference steps",
                minimum=1,
                maximum=100,
                step=1,
                value=30,
            )

        with gr.Accordion("Advanced Settings", open=False):
            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,
                )
            
            with gr.Row():
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,
                )

            with gr.Row():  # Добавляем чекбокс для ControlNet
                use_control_net = gr.Checkbox(
                    label="Use ControlNet",
                    value=False,
                )

            with gr.Row(visible=False, id="control_net_row"):  # Скрываем элемент по умолчанию
                control_net_weight = gr.Slider(
                    label="ControlNet Weight",
                    minimum=0.0,
                    maximum=1.0,
                    step=0.01,
                    value=1.0,
                )

        gr.Examples(examples=examples, inputs=[prompt])
        gr.Examples(examples=examples_negative, inputs=[negative_prompt])
        
        run_button = gr.Button("Run", scale=1, variant="primary")
        result = gr.Image(label="Result", show_label=False)
    
    def toggle_control_net_visibility(use_control_net):
        return {"visible": use_control_net}

    use_control_net.change(fn=toggle_control_net_visibility, inputs=[use_control_net], outputs=["control_net_row"])

    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            width,
            height,
            num_inference_steps,
            model,
            seed,
            guidance_scale,
            lora_scale,
            use_control_net,  # Передаем состояние чекбокса
            control_net_weight,  # Передаем вес ControlNet
        ],
        outputs=[result],
    )

if __name__ == "__main__":
    demo.launch()