import torch
from diffusers import StableDiffusionPipeline
import gradio as gr

model_id = "SG161222/RealVisXL_V4.0"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.to("cpu")  # Use "cuda" if GPU is available

unet = pipe.unet

def generate_image(prompt, unet):
    added_cond_kwargs = {"text_embeds": pipe.get_text_embedding(prompt)}
    image = unet(prompt, **added_cond_kwargs).images[0]
    return image

def chatbot(prompt):
    # Generate the image based on the user's input
    image = generate_image(prompt, unet)
    return image
    
# Create the Gradio interface
interface = gr.Interface(
    fn=chatbot,
    inputs="text",
    outputs="image",
    title="RealVisXL V4.0 Text-to-Image Chatbot",
    description="Enter a text prompt and get an AI-generated image."
)

# Launch the interface
interface.launch()