Update app.py

app.py

@@ -66,12 +66,10 @@ pipe_edit = StableDiffusionXLInstructPix2PixPipeline.from_single_file(
     edit_file, num_in_channels=8, is_cosxl_edit=True, vae=vae, torch_dtype=torch.float16,
 )
 pipe_edit.scheduler = EDMEulerScheduler(sigma_min=0.002, sigma_max=120.0, sigma_data=1.0, prediction_type="v_prediction")
-pipe_edit.load_lora_weights("KingNish/Better-Image-XL-Lora", weight_name="example-03.safetensors", adapter_name="lora")
-pipe_edit.set_adapters(["lora"])
 pipe_edit.to("cuda")
 
 # Generator
-@spaces.GPU(duration=30, queue=False)
+@spaces.GPU(duration=45, queue=False)
 def king(type ,
         input_image ,
         instruction: str ,
@@ -106,12 +104,12 @@ def king(type ,
         generator = torch.Generator().manual_seed(seed)
         if style=="3D":
             instruction = f"3DRenderAF, 3D Render, {instruction}"
-            image = pipe_3D( prompt = instruction, guidance_scale = 5, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
+            image = pipe_3D( prompt = instruction, guidance_scale = 4, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
         elif style=="Logo":
             instruction = f"LogoRedAF, {instruction}"
-            image = pipe_logo( prompt = instruction, guidance_scale = 5, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
+            image = pipe_logo( prompt = instruction, guidance_scale = 4, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
         else:
-            image = pipe_best( prompt = instruction, guidance_scale = 5, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
+            image = pipe_best( prompt = instruction, guidance_scale = 4, num_inference_steps = steps, width = width, height = height, generator = generator).images[0]         
         return seed, image
 
 client = InferenceClient()