app.py

import gradio as gr
import numpy as np

import spaces
import torch
import spaces

from diffusers import FluxControlPipeline, FluxTransformer2DModel
from image_gen_aux import DepthPreprocessor
from diffusers.utils import load_image

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

pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-Depth-dev", revision="refs/pr/1", torch_dtype=torch.bfloat16).to("cuda")
processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")

@spaces.GPU
def infer(control_image, prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
    
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
        
    control_image = processor(control_image)[0].convert("RGB")
    image = pipe(
        prompt=prompt,
        control_image=control_image,
        height=width,
        width=width,
        num_inference_steps=num_inference_steps,
        guidance_scale=guidance_scale,
        generator=torch.Generator().manual_seed(seed),
    ).images[0]
    return 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 Depth [dev]
12B param rectified flow transformer structural conditioning tuned, guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)  
[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]
        """)

        control_image = gr.Image(label="Upload the image for control")
        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)
            
            with gr.Row():
                
                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,
                )
            
            with gr.Row():

                guidance_scale = gr.Slider(
                    label="Guidance Scale",
                    minimum=1,
                    maximum=15,
                    step=0.1,
                    value=3.5,
                )
  
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=28,
                )

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

demo.launch()