refactor

models.py

@@ -201,18 +201,18 @@ def make_image_controlnet(image: np.ndarray,
     flush()
 
     image = Image.fromarray(image).convert("RGB")
-    controlnet_conditioning_image = Image.fromarray(controlnet_conditioning_image).convert("RGB").filter(ImageFilter.GaussianBlur(radius = 9))
+    controlnet_conditioning_image = Image.fromarray(controlnet_conditioning_image).convert("RGB")#.filter(ImageFilter.GaussianBlur(radius = 9))
     mask_image = Image.fromarray((mask_image * 255).astype(np.uint8)).convert("RGB")
     mask_image_postproc = convolution(mask_image)
 
 
-    st.success(f"{pipe.queue_size} images in the queue, can take up to {(pipe.queue_size)+1 * 10} seconds")
+    st.success(f"{pipe.queue_size} images in the queue, can take up to {(pipe.queue_size+1) * 10} seconds")
     generated_image = pipe(
         prompt=positive_prompt,
         negative_prompt=negative_prompt,
         num_inference_steps=20,
-        strength=[1.00, ],
-        guidance_scale=[7.0],
+        strength=1.00,
+        guidance_scale=7.0,
         generator=[torch.Generator(device="cuda").manual_seed(seed)],
         image=image,
         mask_image=mask_image,
@@ -240,6 +240,7 @@ def make_inpainting(positive_prompt: str,
     pipe = get_inpainting_pipeline()
 
     flush()
+    st.success(f"{pipe.queue_size} images in the queue, can take up to {(pipe.queue_size+1) * 10} seconds")
     image_ = pipe(image=image,
                     mask_image=Image.fromarray((mask_image * 255).astype(np.uint8)),
                     prompt=positive_prompt,