import gradio as gr
import torch

d = "cuda" if torch.cuda.is_available() else False

if d:
    import spaces
    
    from diffusers import FluxPipeline
    
    pipeline = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.float16).to(d)
    #pipeline.enable_model_cpu_offload()
    
    @spaces.GPU(duration=70)
    def generate(prompt, negative_prompt, width, height, sample_steps):
        return pipeline(prompt=f"{prompt}\nDO NOT INCLUDE {negative_prompt}", width=width, height=height, num_inference_steps=sample_steps, guidance_scale=7).images[0]
    
    with gr.Blocks() as demo:
            with gr.Column():
                with gr.Row():
                    with gr.Column():
                        prompt = gr.Textbox(label="Prompt", info="What do you want?", value="Keanu Reeves holding a neon sign reading 'Hello, world!', 32k HDR, paparazzi", lines=4, interactive=True)
                        negative_prompt = gr.Textbox(label="Negative Prompt", info="What do you want to exclude from the image?", value="ugly, low quality", lines=4, interactive=True)
                    with gr.Column():
                        generate_button = gr.Button("Generate")
                        output = gr.Image()
                with gr.Row():
                    with gr.Accordion(label="Advanced Settings", open=False):
                        with gr.Row():
                            with gr.Column():
                                width = gr.Slider(label="Width", info="The width in pixels of the generated image.", value=512, minimum=128, maximum=4096, step=64, interactive=True)
                                height = gr.Slider(label="Height", info="The height in pixels of the generated image.", value=512, minimum=128, maximum=4096, step=64, interactive=True)
                            with gr.Column():
                                sampling_steps = gr.Slider(label="Sampling Steps", info="The number of denoising steps.", value=20, minimum=4, maximum=50, step=1, interactive=True)
            
            generate_button.click(fn=generate, inputs=[prompt, negative_prompt, width, height, sampling_steps], outputs=[output])

else:
    def show_message():
        return "# This is the legacy space. To access the app, [click here](https://huggingface.co/spaces/nroggendorff/flux-lora-tester)"
    
    demo = gr.Interface(fn=show_message, 
                         inputs=None, 
                         outputs="markdown")

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