app.py

from diffusers import LDMTextToImagePipeline
import gradio as gr
import PIL.Image
import numpy as np
import random
import torch

ldm_pipeline = LDMTextToImagePipeline.from_pretrained("dalle-mini/dalle-mega")

def predict(prompt, steps=100, seed=42, guidance_scale=6.0):
    torch.cuda.empty_cache()
    generator = torch.manual_seed(seed)
    images = ldm_pipeline([prompt], generator=generator, num_inference_steps=steps, eta=0.3, guidance_scale=guidance_scale)["sample"]
    return images[0]

random_seed = random.randint(0, 2147483647)
gr.Interface(
    predict,
    inputs=[
        gr.inputs.Textbox(label='Prompt', default='a chalk pastel drawing of a llama wearing a wizard hat'),
        gr.inputs.Slider(1, 100, label='Inference Steps', default=50, step=1),
        gr.inputs.Slider(0, 2147483647, label='Seed', default=random_seed, step=1),
        gr.inputs.Slider(1.0, 20.0, label='Guidance Scale - how much the prompt will influence the results', default=6.0, step=0.1),
    ],
    outputs=gr.Image(shape=[256,256], type="pil", elem_id="output_image"),
    css="#output_image{width: 256px}",
    title="Text-To-Image - 🧨 diffusers library",
    description="This Spaces contains a text-to-image Latent Diffusion process for the <a href=\"https://huggingface.co/spaces/LDY/TextToImage\">main Spaces</a>.",
).launch()