change replicate to deployment instead of model

app.py

@@ -1,25 +1,12 @@
-import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-####
-
 import gradio as gr
 import replicate
 
+DEPLOYMENT_URI = "dd-ds-ai/lora-test-01-deployment-test"
+
 
-def generate_image(lora_scale, guidance_scale, prompt_strength, num_steps, prompt):
-    output = replicate.run(
-        "dd-ds-ai/lora_test_01:70c669221124d8aaf0fc494f9553468bd069483a19e74b2753262008b1e8fbb2",
+def generate_image(deployment_uri, lora_scale, guidance_scale, prompt_strength, num_steps, prompt):
+    deployment = replicate.deployments.get(deployment_uri)
+    prediction = deployment.predictions.create(
         input={
             "model": "dev",
             "lora_scale": lora_scale,
@@ -34,6 +21,7 @@ def generate_image(lora_scale, guidance_scale, prompt_strength, num_steps, promp
             "prompt": prompt
         }
     )
+    prediction.wait()
     image_url = output[0] if output else None
     return image_url
 
@@ -52,7 +40,7 @@ def create_gradio_interface():
     # Gradio Interface
     interface = gr.Interface(
         fn=generate_image,  # Die Funktion, die aufgerufen wird
-        inputs=[lora_scale, guidance_scale, prompt_strength, num_steps, prompt],  # Eingaben
+        inputs=[DEPLOYMENT_URI, lora_scale, guidance_scale, prompt_strength, num_steps, prompt],  # Eingaben
         outputs=gr.Image(label="Generated Image"),  # Ausgabe als Bild
     )