Update app.py

app.py

@@ -8,7 +8,7 @@ if torch.cuda.is_available():
     PYTORCH_CUDA_ALLOC_CONF={'max_split_size_mb': 6000}
     torch.cuda.max_memory_allocated(device=device)
     torch.cuda.empty_cache()
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
     pipe.enable_xformers_memory_efficient_attention()
     pipe = pipe.to(device)
     pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
@@ -18,7 +18,7 @@ if torch.cuda.is_available():
     refiner.enable_sequential_cpu_offload()
     refiner.unet = torch.compile(refiner.unet, mode="reduce-overhead", fullgraph=True)
 else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", use_safetensors=True)
+    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
     pipe = pipe.to(device)
     pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
     refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True)
@@ -27,7 +27,7 @@ else:
 
 def genie (prompt, negative_prompt, height, width, scale, steps, seed, prompt_2, negative_prompt_2, high_noise_frac):
     generator = np.random.seed(0) if seed == 0 else torch.manual_seed(seed)
-    int_image = pipe(prompt, prompt_2=prompt_2, negative_prompt_2=negative_prompt_2, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, num_images_per_prompt=1, generator=generator, output_type="latent").images 
+    int_image = pipe(prompt, prompt_2=prompt_2, height=height, width=width, num_inference_steps=steps, num_images_per_prompt=1, generator=generator, output_type="latent").images 
     image = refiner(prompt=prompt, prompt_2=prompt_2, negative_prompt=negative_prompt, negative_prompt_2=negative_prompt_2, image=int_image, denoising_start=high_noise_frac).images[0]   
     return image