import gradio as gr
import numpy as np
import spaces
import torch
from diffusers import FluxPriorReduxPipeline, FluxPipeline
from diffusers.utils import load_image


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

pipe_prior_redux = FluxPriorReduxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-Redux-dev",
    revision="refs/pr/8",
    torch_dtype=torch.bfloat16
).to("cuda")

pipe = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev" , 
    text_encoder=None,
    text_encoder_2=None,
    torch_dtype=torch.bfloat16
).to("cuda")

@spaces.GPU
def infer(control_image, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
    pipe_prior_output = pipe_prior_redux(control_image)
    images = pipe(
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        generator=torch.Generator("cpu").manual_seed(seed),
        **pipe_prior_output,
    ).images[0]
    return images
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 Redux [dev]
An adapter for FLUX [dev] to create image variations
[[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)]
        """)

        input_image = gr.Image(label="Image to create variations", type="pil")
        run_button = gr.Button("Run")    
        
        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],
        fn = infer,
        inputs = [input_image, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
        outputs = [result, seed]
    )

demo.launch()