from diffusers import StableDiffusionXLPipeline, AutoencoderKL
import torch
import random
#from controlnet_aux import OpenposeDetector
#from diffusers.utils import load_image
import gradio as gr


#model_base = "stabilityai/stable-diffusion-xl-base-1.0"

#model_url = "https://huggingface.co/Krebzonide/Colossus_Project_XL/blob/main/colossusProjectXLSFW_v202BakedVAE.safetensors"
model_url = "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0.safetensors"
#model_url = "https://huggingface.co/Krebzonide/Sevenof9_v3_sdxl/blob/main/nsfwSevenof9V3_nsfwSevenof9V3.safetensors"

vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = None

#pipe = StableDiffusionXLPipeline.from_pretrained(
#    model_base, vae=vae, torch_dtype=torch.float16, variant="fp16", use_safetensors=True
#)


css = """
.btn-green {
  background-image: linear-gradient(to bottom right, #6dd178, #00a613) !important;
  border-color: #22c55e !important;
  color: #166534 !important;
}
.btn-green:hover {
  background-image: linear-gradient(to bottom right, #6dd178, #6dd178) !important;
}
"""

def generate(prompt, neg_prompt, samp_steps, guide_scale, batch_size, seed, height, width, progress=gr.Progress(track_tqdm=True)):
    if seed < 0:
        seed = random.randint(1,999999)
    images = pipe(
        prompt,
        negative_prompt=neg_prompt,
        num_inference_steps=samp_steps,
        guidance_scale=guide_scale,
        #cross_attention_kwargs={"scale": lora_scale},
        num_images_per_prompt=batch_size,
        height=height,
        width=width,
        generator=torch.manual_seed(seed),
    ).images
    return [(img, f"Image {i+1}") for i, img in enumerate(images)]
        
def set_base_model(base_model_id):
    global pipe
    del pipe
    torch.cuda.empty_cache()
    gc.collect()
    pipe = StableDiffusionXLPipeline.from_single_file(
        model_url,
        torch_dtype = torch.float16,
        variant = "fp16",
        vae = vae,
        use_safetensors = True,
        use_auth_token="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"
    )
    #pipe = load_model(base_model_id)
    pipe.to("cuda")
    return pipe

def load_model(base_model_id):
     pipe = StableDiffusionXLPipeline.from_single_file(
        model_url,
        torch_dtype = torch.float16,
        variant = "fp16",
        vae = vae,
        use_safetensors = True,
        use_auth_token="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"
    )
    

with gr.Blocks(css=css) as demo:
    with gr.Column():
        prompt = gr.Textbox(label="Prompt")
        negative_prompt = gr.Textbox(label="Negative Prompt")
        submit_btn = gr.Button("Generate", elem_classes="btn-green")
        with gr.Row():
            samp_steps = gr.Slider(1, 50, value=20, step=1, label="Sampling steps")
            guide_scale = gr.Slider(1, 6, value=3, step=0.5, label="Guidance scale")
            batch_size = gr.Slider(1, 6, value=1, step=1, label="Batch size")
        with gr.Row():
            seed = gr.Slider(label="Seed", value=-1, minimum=-1, maximum=999999, step=1)
            height = gr.Slider(label="Height", value=1024, minimum=512, maximum=2048, step=16)
            width = gr.Slider(label="Width", value=1024, minimum=512, maximum=2048, step=16)
        gallery = gr.Gallery(label="Generated images", height=800)

    submit_btn.click(generate, [prompt, negative_prompt, samp_steps, guide_scale, batch_size, seed, height, width], [gallery], queue=True)

pipe = set_base_model(model_url)
demo.queue(1)
demo.launch(debug=True)