app.py

import gradio as gr
import numpy as np
import random

import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline
import torch
import subprocess
from transformers import IdeficsForVisionText2Text, AutoProcessor

subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", env={}, shell=True)

# Load FLUX image generator
device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "black-forest-labs/FLUX.1-schnell"  # Replace to the model you would like to use
lora_path = "matteomarjanovic/flatsketcher"
weigths_file = "lora.safetensors"

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)
pipe.load_lora_weights(lora_path, weight_name=weigths_file)

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

# Load IDEFICS model for generate the prompt
checkpoint = "HuggingFaceM4/idefics-9b"
processor = AutoProcessor.from_pretrained(checkpoint)
idefics_model = IdeficsForVisionText2Text.from_pretrained(checkpoint, torch_dtype=torch.bfloat16, device_map="auto")


@spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    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,
        negative_prompt=negative_prompt,
        guidance_scale=0.,
        num_inference_steps=4,
        width=1420,
        height=1080,
        max_sequence_length=256,
    ).images[0]

    return image, seed

@spaces.GPU #[uncomment to use ZeroGPU]
def generate_description_fn(
    image,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    prompt = [
        "https://images.unsplash.com/photo-1583160247711-2191776b4b91?ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D&auto=format&fit=crop&w=3542&q=80",
    ]

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

    inputs = processor(prompt, return_tensors="pt").to("cuda")
    bad_words_ids = processor.tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids

    generated_ids = idefics_model.generate(**inputs, max_new_tokens=10, bad_words_ids=bad_words_ids)
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)

    return generated_text[0]


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;
}
"""

generated_prompt = ""

with gr.Blocks(css=css) as demo:
    with gr.Row():
        with gr.Column(elem_id="col-input-image"):
            gr.Markdown(" # Drop your image here")
            input_image = gr.Image()
            generate_button = gr.Button("Generate", scale=0, variant="primary")
            generated_prompt_md = gr.Markdown(generated_prompt)
        with gr.Column(elem_id="col-container"):
            gr.Markdown(" # Text-to-Image Gradio Template")

            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=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,  # 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=2,  # 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=[
                input_image
            ],
            outputs=[generated_prompt],
        )

        gr.on(
            triggers=[generate_button.click],
            fn=generate_description_fn,
            inputs=[
                input_image,
                seed,
                randomize_seed,
                width,
                height,
                guidance_scale,
                num_inference_steps,
            ],
            outputs=[result, seed],
        )

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