Update app.py

app.py

@@ -87,7 +87,7 @@ pipe.to(device)
 
 pipe.enable_vae_slicing()
 pipe.enable_vae_tiling()
-pipe.enable_xformers_memory_efficient_attention()
+
 @spaces.GPU(duration=120)
 def generate_image(
     upload_images, 
@@ -165,22 +165,23 @@ def generate_image(
     if start_merge_step > 30:
         start_merge_step = 30
     print(start_merge_step)
-    images = pipe(
-        prompt=prompt,
-        width=output_w,
-        height=output_h,
-        input_id_images=input_id_images,
-        negative_prompt=negative_prompt,
-        num_images_per_prompt=num_outputs,
-        num_inference_steps=num_steps,
-        start_merge_step=start_merge_step,
-        generator=generator,
-        guidance_scale=guidance_scale,
-        id_embeds=id_embeds,
-        image=sketch_image,
-        adapter_conditioning_scale=adapter_conditioning_scale,
-        adapter_conditioning_factor=adapter_conditioning_factor,
-    ).images
+    with torch.no_grad(), torch.inference_mode():
+        images = pipe(
+            prompt=prompt,
+            width=output_w,
+            height=output_h,
+            input_id_images=input_id_images,
+            negative_prompt=negative_prompt,
+            num_images_per_prompt=num_outputs,
+            num_inference_steps=num_steps,
+            start_merge_step=start_merge_step,
+            generator=generator,
+            guidance_scale=guidance_scale,
+            id_embeds=id_embeds,
+            image=sketch_image,
+            adapter_conditioning_scale=adapter_conditioning_scale,
+            adapter_conditioning_factor=adapter_conditioning_factor,
+        ).images
     return images, gr.update(visible=True)
 
 def swap_to_gallery(images):