Update app.py

app.py

@@ -12,14 +12,14 @@ torch.cuda.max_memory_allocated(device=device)
 torch.cuda.empty_cache()
 pipe = StableCascadeCombinedPipeline.from_pretrained("stabilityai/stable-cascade", variant="bf16", torch_dtype=torch.bfloat16)
 pipe.enable_model_cpu_offload()
-#pipe.enable_xformers_memory_efficient_attention()
-#pipe = pipe.to(device)
+pipe.enable_xformers_memory_efficient_attention()
+pipe = pipe.to(device)
 torch.cuda.empty_cache()
             
          
 def genie (Prompt, negative_prompt, height, width, scale, steps, seed, upscale):
     generator = np.random.seed(0) if seed == 0 else torch.manual_seed(seed)
-    #torch.cuda.empty_cache()
+    torch.cuda.empty_cache()
     image=pipe(prompt=Prompt,
     negative_prompt="",
     num_inference_steps=20,
@@ -30,7 +30,7 @@ def genie (Prompt, negative_prompt, height, width, scale, steps, seed, upscale):
     #int_image = pipe(prompt=Prompt, negative_prompt=negative_prompt, num_inference_steps=steps, guidance_scale=scale, width=width, height=height, output_type="latent").images #
     #torch.cuda.empty_cache()
     #image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=.99).images[0]
-    #torch.cuda.empty_cache()
+    torch.cuda.empty_cache()
     return image
     
 gr.Interface(fn=genie, inputs=[gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'),