Update app.py

app.py

@@ -255,10 +255,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
                return image
 
     if Model == "SDXL 1.0":
-        #from diffusers import StableCascadeCombinedPipeline
-
-        #sdxl = StableCascadeCombinedPipeline.from_pretrained("stabilityai/stable-cascade", variant="bf16", torch_dtype=torch.bfloat16)
-
+        
         torch.cuda.empty_cache()
         torch.cuda.max_memory_allocated(device=device)
         sdxl = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
@@ -269,7 +266,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
         if refine == "Yes":
             torch.cuda.max_memory_allocated(device=device)
             torch.cuda.empty_cache()
-            image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=10, prior_num_inference_steps=20, prior_guidance_scale=3.0, output_type="latent").images
+            image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
             torch.cuda.empty_cache()
             sdxl = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
             sdxl.enable_xformers_memory_efficient_attention()
@@ -301,7 +298,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
                 return upscaled
             else:
                 
-               image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=10, prior_num_inference_steps=20, guidance_scale=3).images[0]
+               image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
                torch.cuda.empty_cache()
                       
     return image