app.py

import gradio as gr
from huggingface_hub import login
import os 
is_shared_ui = True if "fffiloni/sd-xl-custom-model" in os.environ['SPACE_ID'] else False
hf_token = os.environ.get("HF_TOKEN")
login(token=hf_token)

import torch
from diffusers import DiffusionPipeline, AutoencoderKL

vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)

pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    vae=vae, torch_dtype=torch.float16, variant="fp16",
    use_safetensors=True
)

device="cuda" if torch.cuda.is_available() else "cpu"

pipe.to(device)

def load_model(custom_model, weight_name):
    
    if custom_model == "":
        gr.Warning("If you want to use a private model, you need to duplicate this space on your personal account.")
        raise gr.Error("You forgot to define Model ID.")
    
    # This is where you load your trained weights
    pipe.load_lora_weights(custom_model, weight_name=weight_name, use_auth_token=True)
    
    return "Model loaded!"

def infer (prompt, inf_steps, guidance_scale, seed, lora_weight, progress=gr.Progress(track_tqdm=True)):
    
    generator = torch.Generator(device="cuda").manual_seed(seed)
    
    image = pipe(
        prompt=prompt, 
        num_inference_steps=inf_steps,
        guidance_scale = guidance_scale,
        generator=generator,
        cross_attention_kwargs={"scale": lora_weight}
    ).images[0]
    
    return image

css="""
#col-container{
    margin: 0 auto;
    max-width: 680px;
    text-align: left;
}
div#warning-duplicate {
    background-color: #ebf5ff;
    padding: 0 10px 5px;
    margin: 20px 0;
}
div#warning-duplicate > .gr-prose > h2, div#warning-duplicate > .gr-prose > p {
    color: #0f4592!important;
}
div#warning-duplicate strong {
    color: #0f4592;
}
p.actions {
    display: flex;
    align-items: center;
    margin: 20px 0;
}
div#warning-duplicate .actions a {
    display: inline-block;
    margin-right: 10px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        if is_shared_ui:
            top_description = gr.HTML(f'''
                <div class="gr-prose">
                    <h2><svg xmlns="http://www.w3.org/2000/svg" width="18px" height="18px" style="margin-right: 0px;display: inline-block;"fill="none"><path fill="#fff" d="M7 13.2a6.3 6.3 0 0 0 4.4-10.7A6.3 6.3 0 0 0 .6 6.9 6.3 6.3 0 0 0 7 13.2Z"/><path fill="#fff" fill-rule="evenodd" d="M7 0a6.9 6.9 0 0 1 4.8 11.8A6.9 6.9 0 0 1 0 7 6.9 6.9 0 0 1 7 0Zm0 0v.7V0ZM0 7h.6H0Zm7 6.8v-.6.6ZM13.7 7h-.6.6ZM9.1 1.7c-.7-.3-1.4-.4-2.2-.4a5.6 5.6 0 0 0-4 1.6 5.6 5.6 0 0 0-1.6 4 5.6 5.6 0 0 0 1.6 4 5.6 5.6 0 0 0 4 1.7 5.6 5.6 0 0 0 4-1.7 5.6 5.6 0 0 0 1.7-4 5.6 5.6 0 0 0-1.7-4c-.5-.5-1.1-.9-1.8-1.2Z" clip-rule="evenodd"/><path fill="#000" fill-rule="evenodd" d="M7 2.9a.8.8 0 1 1 0 1.5A.8.8 0 0 1 7 3ZM5.8 5.7c0-.4.3-.6.6-.6h.7c.3 0 .6.2.6.6v3.7h.5a.6.6 0 0 1 0 1.3H6a.6.6 0 0 1 0-1.3h.4v-3a.6.6 0 0 1-.6-.7Z" clip-rule="evenodd"/></svg>
                    Note: you might want to use a private custom LoRa model</h2>
                    <p class="main-message">
                        To do so, <strong>duplicate the Space</strong> and run it on your own profile using <strong>your own access token</strong> and eventually a GPU (T4-small or A10G-small) for faster inference without waiting in the queue.<br />
                    </p>
                    <p class="actions">
                        <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}?duplicate=true">
                            <img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/duplicate-this-space-lg-dark.svg" alt="Duplicate this Space" />
                        </a>
                        to start using private models and skip the queue
                    </p>
                </div>
            ''', elem_id="warning-duplicate")
        gr.HTML("""
<h2 style="text-align: center;">SD-XL Custom Model Inference</h2>
<p style="text-align: center;">Use this demo to check results from your previously trained LoRa model.</p>
        """)
        with gr.Row():
            with gr.Column():
                custom_model = gr.Textbox(label="Your custom model ID", placeholder="your_username/your_trained_model_name", info="Make sure your model is set to PUBLIC ")
                weight_name = gr.Textbox(label="Safetensors file", value="pytorch_lora_weights.safetensors", info="specify which one if model has several .safetensors files")
            with gr.Column():
                load_model_btn = gr.Button("Load my model")
                model_status = gr.Textbox(label="model status", interactive=False)
        
        prompt_in = gr.Textbox(label="Prompt")   
        with gr.Row():
            inf_steps = gr.Slider(
                label="Inference steps",
                minimum=12,
                maximum=50,
                step=1,
                value=25
            )
            guidance_scale = gr.Slider(
                label="Guidance scale",
                minimum=0.0,
                maximum=50.0,
                step=0.1,
                value=7.5
            )
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=500000,
                step=1,
                value=42
            )
        lora_weight = gr.Slider(
            label="LoRa weigth",
            minimum=0.0,
            maximum=1.0,
            step=0.01,
            value=0.9
        )
        submit_btn = gr.Button("Submit")
        image_out = gr.Image(label="Image output")

    load_model_btn.click(
        fn = load_model,
        inputs=[custom_model, weight_name],
        outputs = [model_status]
    )
    submit_btn.click(
        fn = infer,
        inputs = [prompt_in, inf_steps, guidance_scale, seed, lora_weight],
        outputs = [image_out]
    )

demo.queue().launch()