Update app.py

app.py

@@ -31,54 +31,48 @@ app.config['generation_thread'] = None
 #       return jsonify({"error": f"Failed to download model: {str(e)}"}), 500
 
 def generate_image_gif(prompt):
-  global pipe
-  if pipe is None:
+    print('Downloading the model weights')
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    xm = load_model('transmitter', device=device)
+    model = load_model('text300M', device=device)
+    diffusion = diffusion_from_config(load_config('diffusion'))
+
     try:
-        print('Downloading the model weights')
-        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-        xm = load_model('transmitter', device=device)
-        model = load_model('text300M', device=device)
-        diffusion = diffusion_from_config(load_config('diffusion'))
-        pipe = 'Model loaded'
+        batch_size = 1
+        guidance_scale = 30.0
+    
+        latents = sample_latents(
+            batch_size=batch_size,
+            model=model,
+            diffusion=diffusion,
+            guidance_scale=guidance_scale,
+            model_kwargs=dict(texts=[prompt] * batch_size),
+            progress=True,
+            clip_denoised=True,
+            use_fp16=True,
+            use_karras=True,
+            karras_steps=64,
+            sigma_min=1E-3,
+            sigma_max=160,
+            s_churn=0,
+        )
+        render_mode = 'nerf'
+        size = 256
+        # render_mode = 'nerf' # you can change this to 'stf'
+        # size =  # this is the size of the renders, higher values take longer to render.
+    
+        cameras = create_pan_cameras(size, device)
+        images = decode_latent_images(xm, latents, cameras, rendering_mode=render_mode)
+        writer = io.BytesIO()
+        images[0].save(writer, format="GIF", save_all=True, append_images=images[1:], duration=100, loop=0)
+        writer.seek(0)
+        data = base64.b64encode(writer.read()).decode("ascii")
+        response_data = {'video_base64': data,'status':None}
+        print('response_data',response_data)
+        return response_data
     except Exception as e:
-        print(f"Error downloading the model: {e}")
-
-  try:
-    batch_size = 1
-    guidance_scale = 30.0
-
-    latents = sample_latents(
-        batch_size=batch_size,
-        model=model,
-        diffusion=diffusion,
-        guidance_scale=guidance_scale,
-        model_kwargs=dict(texts=[prompt] * batch_size),
-        progress=True,
-        clip_denoised=True,
-        use_fp16=True,
-        use_karras=True,
-        karras_steps=64,
-        sigma_min=1E-3,
-        sigma_max=160,
-        s_churn=0,
-    )
-    render_mode = 'nerf'
-    size = 256
-    # render_mode = 'nerf' # you can change this to 'stf'
-    # size =  # this is the size of the renders, higher values take longer to render.
-
-    cameras = create_pan_cameras(size, device)
-    images = decode_latent_images(xm, latents, cameras, rendering_mode=render_mode)
-    writer = io.BytesIO()
-    images[0].save(writer, format="GIF", save_all=True, append_images=images[1:], duration=100, loop=0)
-    writer.seek(0)
-    data = base64.b64encode(writer.read()).decode("ascii")
-    response_data = {'video_base64': data,'status':None}
-    print('response_data',response_data)
-    return response_data
-  except Exception as e:
-    print(f"Error generating 3D: {e}")
-    return jsonify({"error": f"Failed to generate 3D animation: {str(e)}"}), 500
+        print(f"Error generating 3D: {e}")
+        return jsonify({"error": f"Failed to generate 3D animation: {str(e)}"}), 500
 
 def background(prompt):
   with app.app_context():