main_gr.py

import gradio as gr
import numpy as np
import random
import spaces
import torch
from diffusers import DiffusionPipeline
from pruna import SmashConfig, smash

dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)


# Initialize the SmashConfig
smash_config = SmashConfig()
smash_config['compilers'] = ['flux_caching']
smash_config['comp_flux_caching_cache_interval'] = 4 # Higher is faster, but reduces quality
smash_config['comp_flux_caching_start_step'] = 4 # Best to keep it as the same as cache_interval
smash_config['comp_flux_caching_compile'] = True # Whether to additionally compile the model for extra speed up
smash_config['comp_flux_caching_save_model'] = False # Whether to save the model after compilation or just use it for inference

pipe = smash(
    model=pipe,
    token='None',  # replace <your-token> with your actual token or set to None if you do not have one yet
    smash_config=smash_config,
)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 4096

@spaces.GPU()
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, progress=gr.Progress(track_tqdm=True)):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator().manual_seed(seed)
    image = pipe(
            prompt = prompt, 
            width = width,
            height = height,
            num_inference_steps = num_inference_steps, 
            generator = generator,
            guidance_scale=0.0
    ).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 [schnell]
12B param rectified flow transformer distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
[[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-schnell)]
        """)
        
        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():
                
  
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=4,
                )
        
        gr.Examples(
            examples = examples,
            fn = infer,
            inputs = [prompt],
            outputs = [result, seed],
            cache_examples="lazy"
        )

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

demo.launch(share=True)