app.py

import gradio as gr
from diffusers import DiffusionPipeline
from transformers import pipeline

get_caption = pipeline("image-to-text",model="Salesforce/blip-image-captioning-base")

def captioner(input):
    output = get_caption(input)
    return output[0]['generated_text']

generate_pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")

def generate(prompt):
    return generate_pipeline(prompt).images[0]

def caption_and_generate(image):
    caption = captioner(image)
    image = generate(caption)
    return [caption, image]

with gr.Blocks() as demo:
    gr.Markdown("# Describe-and-Generate game 🖍️")
    image_upload = gr.Image(label="Your first image",type="pil")
    btn_all = gr.Button("Caption and generate")
    caption = gr.Textbox(label="Generated caption")
    image_output = gr.Image(label="Generated Image")

    btn_all.click(fn=caption_and_generate, inputs=[image_upload], outputs=[caption, image_output])

demo.launch()