changes

app.py

@@ -1,19 +1,25 @@
 import gradio as gr
-from diffusers import DiffusionPipeline
-import torch
+import requests
+import os
 
-# Initialize the model pipeline
-pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", 
-                                         torch_dtype=torch.float16, 
-                                         use_safetensors=True, 
-                                         variant="fp16")
+api_key = os.getenv("HF_API_KEY")
+# Define the Hugging Face API endpoint and your API key
+api_url = "https://api-inference.huggingface.co/models/stabilityai/stable-diffusion-xl-base-1.0"
+headers = {"Authorization": f"Bearer {api_key}"}
 
-pipe.to("cuda" if torch.cuda.is_available() else "cpu")
-
-# Define the inference function
+# Define the inference function using the Hugging Face API
 def generate_image(prompt):
-    image = pipe(prompt).images[0]
-    return image
+    payload = {
+        "inputs": prompt
+    }
+    response = requests.post(api_url, headers=headers, json=payload)
+    
+    if response.status_code == 200:
+        # If the response is successful, return the image
+        image = response.content
+        return image
+    else:
+        return "Error: " + response.text
 
 # Create the Gradio interface
 iface = gr.Interface(fn=generate_image, inputs="text", outputs="image", live=True)

requirements.txt

@@ -1,3 +1,5 @@
 diffusers
 torch
 gradio
+accelerate
+python-dotenv