app.py

import os
import gradio as gr
import numpy as np
import random

import spaces
from diffusers import DiffusionPipeline
import torch

model_repo_id = "Qwen/Qwen-Image" 
hf_token = os.getenv("HF_TOKEN_SPACES")

MODEL_CHOICES = [
    "black-forest-labs/FLUX.1-dev",
    "Qwen/Qwen-Image",
    "tencent/HunyuanImage-3.0",
    "stabilityai/stable-diffusion-3.5-medium",
    "stabilityai/stable-diffusion-2-1",
    "SG161222/Realistic_Vision_V5.1_noVAE"
]

if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype, use_auth_token=hf_token)
pipe = pipe.to(device)

current_model_id = model_repo_id

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


@spaces.GPU
def infer(
    model_name,  
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    progress=gr.Progress(track_tqdm=True),
):

    global pipe, current_model_id

    # reload pipeline if user picked a different model
    if model_name != current_model_id:
        pipe = DiffusionPipeline.from_pretrained(
            model_name,
            torch_dtype=torch_dtype,
            use_auth_token=hf_token
        ).to(device)
        current_model_id = model_name

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    generator = torch.Generator().manual_seed(seed)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed


examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

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

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Transform Text to Images")

        with gr.Row():
            model_dropdown = gr.Dropdown(
                label="Diffusion model",
                choices=MODEL_CHOICES,
                value=model_repo_id,
                )

        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, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=True,
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )

            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,  # Replace with defaults that work for your model
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=0.0,  # Replace with defaults that work for your model
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=50,  # Replace with defaults that work for your model
                )

        gr.Examples(examples=examples, inputs=[prompt])
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            model_dropdown, 
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

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