app.py

import torch
from diffusers import StableDiffusion3Pipeline
import gradio as gr
import os
import transformers
import numpy as np
from transformers import T5Tokenizer, T5ForConditionalGeneration
import spaces

HF_TOKEN = os.getenv("HF_TOKEN")

if torch.cuda.is_available():
    device = "cuda"
    print("Using GPU")
else:
    device = "cpu"
    print("Using CPU")


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


# Initialize the pipeline and download the sd3 medium model
pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16)
pipe.to(device)

# superprompt-v1
tokenizer = T5Tokenizer.from_pretrained("roborovski/superprompt-v1")
model = T5ForConditionalGeneration.from_pretrained("roborovski/superprompt-v1", device_map="auto", torch_dtype="auto")
model.to(device)

# Define the image generation function
@spaces.GPU(duration=90)
def generate_image(prompt, enhance_prompt, negative_prompt, num_inference_steps, height, width, guidance_scale, seed, num_images_per_prompt):
    if seed == 0:
        seed = random.randint(1, 2**32-1)
        
    if enhance_prompt:
        transformers.set_seed(seed)
        
        input_text = f"Expand the following prompt to add more detail: {prompt}"
        input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(device)
        
        outputs = model.generate(
        input_ids,
        max_new_tokens=512,
        repetition_penalty=1.2,
        do_sample=True,
        temperature=0.7,
        top_p=1,
        top_k=50
        )
        prompt = tokenizer.decode(outputs[0], skip_special_tokens=True)
        
    generator = torch.Generator().manual_seed(seed)
    
    output = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        num_inference_steps=num_inference_steps,
        height=height,
        width=width,
        guidance_scale=guidance_scale,
        generator=generator,
        num_images_per_prompt=num_images_per_prompt
    ).images
    return output

# Create the Gradio interface

prompt = gr.Textbox(label="Prompt", info="Describe the image you want", placeholder="A cat...")

enhance_prompt = gr.Checkbox(label="Prompt Enhancement", info="Enhance your prompt with SuperPrompt-v1", value=True)

negative_prompt = gr.Textbox(label="Negative Prompt", info="Describe what you don't want in the image", value="deformed, distorted, disfigured, poorly drawn, bad anatomy, incorrect anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation", placeholder="Ugly, bad anatomy...")

num_inference_steps = gr.Slider(label="Number of Inference Steps", info="The number of denoising steps of the image. More denoising steps usually lead to a higher quality image at the cost of slower inference", minimum=1, maximum=50, value=25)

height = gr.Slider(label="Height", info="Height of the Image", minimum=256, maximum=1344, step=32, value=1024)

width = gr.Slider(label="Width", info="Width of the Image", minimum=256, maximum=1344, step=32, value=1024)

guidance_scale = gr.Slider(label="Guidance Scale", info="Controls how much the image generation process follows the text prompt. Higher values make the image stick more closely to the input text.", minimum=0.0, maximum=10.0, value=7.5, step=0.1)

seed = gr.Slider(value=42, minimum=0, maximum=MAX_SEED, step=1, label="Seed", info="A starting point to initiate the generation process, put 0 for a random one")

num_images_per_prompt = gr.Slider(label="Number of Images to generate with the settings",minimum=1, maximum=4, step=1, value=1)

interface = gr.Interface(
    fn=generate_image,
    inputs=[prompt, enhance_prompt, negative_prompt, num_inference_steps, height, width, guidance_scale, seed, num_images_per_prompt],
    outputs=gr.Gallery(label="Generated AI Images", elem_id="gallery", show_label=False),
    title="Stable Diffusion 3 Medium",
    description="Made by <a href='https://linktr.ee/Nick088' target='_blank'>Nick088</a> \n Join https://discord.gg/osai to talk about Open Source AI"
)

# Launch the interface
interface.launch(share = False)