Update app.py

app.py

@@ -1,42 +1,18 @@
 import gradio as gr
-import transforms
 import requests
 import io
 from PIL import Image
 from transformers import pipeline
-from torchvision import transforms
 
 title = "Fine Tuned SD Model - Authoral stylization"
 description = "Generate images trained in an authoral illustration model."
 article = "<p style='text-align: center'><a href='https://news.machinelearning.sg/posts/beautiful_profile_pics_remove_background_image_with_deeplabv3/'>Blog</a> | <a href='https://github.com/eugenesiow/practical-ml'>Github Repo</a></p>"
 
+def generate_image(prompt):
+    model = pipeline("image-to-image", model="Cacau/heart-of-painting")
+    return model(prompt)[0]
 
-gr.Interface.load(
-  "spaces/Cacau/heart-of-painting",
+inputs = gr.inputs.Textbox(label="Prompt", placeholder="Your prompt here...")
+output = gr.outputs.Image(label="Generated Image")
 
-demo = gr.Interface(
-    fn=greet,
-    inputs=gr.Textbox(lines=2, placeholder="Name Here..."),
-    outputs="text",
-)
-
-
-with gr.Blocks(theme=gr.themes.Glass()) as demo:
-   inputs=[gr.Textbox(label="Prompt", source="input box")]
-output=[gr.Ima]
-).launch()
-    
-def query(payload):
-	response = requests.post(API_URL, headers=headers, json=payload)
-	return response.content
-image_bytes = query({
-	"inputs":gr.Textbox(lines=2, placeholder="Your prompt here..."),    
-})
-
-# You can access the image with PIL.Image for example
-import io
-from PIL import Image
-image = Image.open(io.BytesIO(image_bytes))
-
-return "This is your generated image:" + image "**Save it in your files!"
-demo.launch()
+gr.Interface(generate_image, inputs, output, title=title, description=description, article=article).launch()