app.py

import os
import gradio as gr
import numpy as np
from gradio_client import Client

MODEL_ID = os.getenv("MODEL_ID", "KingNish/SDXL-Flash")
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
BATCH_SIZE = int(os.getenv("BATCH_SIZE", "1"))

client = Client(MODEL_ID)

examples = [
    "a cat eating a piece of cheese",
    "a ROBOT riding a BLUE horse on Mars, photorealistic, 4k",
    "Ironman VS Hulk, ultrarealistic",
    "Astronaut in a jungle, cold color palette, oil pastel, detailed, 8k",
    "An alien holding a sign board containing the word 'Flash', futuristic, neonpunk",
    "Kids going to school, Anime style"
]

css = '''
.gradio-container{max-width: 700px !important}
h1{text-align:center}
footer {
    visibility: hidden
}
'''

with gr.Blocks(css=css) as demo:
    gr.Markdown("""# SDXL Flash""")
    with gr.Group():
        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.Gallery(label="Result", columns=1, show_label=False)
    with gr.Accordion("Advanced options", open=False):
        num_images = gr.Slider(
            label="Number of Images",
            minimum=1,
            maximum=4,
            step=1,
            value=1,
        )
        with gr.Row():
            use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=5,
                lines=4,
                placeholder="Enter a negative prompt",
                value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW",
                visible=True,
            )
        seed = gr.Slider(
            label="Seed",
            minimum=0,
            maximum=np.iinfo(np.int32).max,
            step=1,
            value=0,
        )
        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
        with gr.Row(visible=True):
            width = gr.Slider(
                label="Width",
                minimum=512,
                maximum=MAX_IMAGE_SIZE,
                step=64,
                value=1024,
            )
            height = gr.Slider(
                label="Height",
                minimum=512,
                maximum=MAX_IMAGE_SIZE,
                step=64,
                value=1024,
            )
        with gr.Row():
            guidance_scale = gr.Slider(
                label="Guidance Scale",
                minimum=0.1,
                maximum=6,
                step=0.1,
                value=3.0,
            )
            num_inference_steps = gr.Slider(
                label="Number of inference steps",
                minimum=1,
                maximum=15,
                step=1,
                value=8,
            )

    gr.Examples(
        examples=examples,
        inputs=prompt,
        cache_examples=False
    )

    use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt,
        outputs=negative_prompt,
        api_name=False,
    )

    def generate(
        prompt,
        negative_prompt,
        use_negative_prompt,
        seed,
        width,
        height,
        guidance_scale,
        num_inference_steps,
        randomize_seed,
        num_images,
    ):
        results = []
        for _ in range(num_images):
            response = client.predict(
                prompt=prompt,
                negative_prompt=negative_prompt if use_negative_prompt else "",
                use_negative_prompt=use_negative_prompt,
                seed=seed,
                width=width,
                height=height,
                guidance_scale=guidance_scale,
                num_inference_steps=num_inference_steps,
                randomize_seed=randomize_seed,
                use_resolution_binning=True,
                api_name="/run"
            )
            if isinstance(response, list) and response[0].get("image"):
                results.append(response[0]["image"])
            else:
                results.append("")
        return results, seed

    gr.on(
        triggers=[
            prompt.submit,
            negative_prompt.submit,
            run_button.click,
        ],
        fn=generate,
        inputs=[
            prompt,
            negative_prompt,
            use_negative_prompt,
            seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
            randomize_seed,
            num_images
        ],
        outputs=[result, seed],
        api_name="run",
    )

if __name__ == "__main__":
    demo.queue(max_size=20).launch()