import torch
from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, EulerDiscreteScheduler
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
import gradio as gr
import spaces


base = "stabilityai/stable-diffusion-xl-base-1.0"
repo = "ByteDance/SDXL-Lightning"
ckpt = "sdxl_lightning_1step_unet_x0.safetensors" # Use the correct ckpt for your step setting!
unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)
unet.load_state_dict(load_file(hf_hub_download(repo, ckpt), device="cuda"))
pipe = StableDiffusionXLPipeline.from_pretrained(base, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
# Ensure sampler uses "trailing" timesteps and "sample" prediction type.
pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing", prediction_type="sample")
# Load model.
@spaces.GPU
def generate(prompt):
    image = pipe(prompt, num_inference_steps=1, guidance_scale=0).images[0]
    return image

output_image = gr.Image(type="pil")
demo = gr.Interface(fn=generate, inputs="text", outputs=output_image)

if __name__ == "__main__":
    unet = UNet2DConditionModel.from_config(base, subfolder="unet").to("cuda", torch.float16)
    unet.load_state_dict(load_file(hf_hub_download(repo, ckpt), device="cuda"))
    pipe = StableDiffusionXLPipeline.from_pretrained(base, unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")
    # Ensure sampler uses "trailing" timesteps and "sample" prediction type.
    pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing", prediction_type="sample")
    demo.launch()