Update app.py

app.py

@@ -18,9 +18,7 @@ pipe_prior = accelerator.prepare(KandinskyV22PriorPipeline.from_pretrained("kand
 pipe_prior.to("cpu")
 pipe = accelerator.prepare(KandinskyV22ControlnetPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-controlnet-depth", torch_dtype=torch.float32, use_safetensors=False))
 pipe.to("cpu")
-##pipe.unet.to(memory_format=torch.channels_last)
-##qrocessor = GLPNImageProcessor.from_pretrained("vinvino02/glpn-nyu")
-##zodel = GLPNForDepthEstimation.from_pretrained("vinvino02/glpn-nyu")
+
 generator = torch.Generator(device="cpu").manual_seed(random.randint(0, MAX_SEED))
 
 def make_hint(image, depth_estimator):
@@ -28,58 +26,17 @@ def make_hint(image, depth_estimator):
     image = np.array(image)
     image = image[:, :, None]
     image = np.concatenate([image, image, image], axis=2)
-    ##hint = Image.fromarray(image)
+    
     detected_map = torch.from_numpy(image).float() / 255.0
     hint = detected_map.permute(2, 0, 1)
-    ##deputs = qrocessor(images=image, return_tensors="pt")
-    ##with torch.no_grad():
-    ##    edputs = zodel(**deputs)
-    ##    predicted_depth = edputs.predicted_depth
-
-    # interpolate to original size
-    ##prediction = torch.nn.functional.interpolate(
-    ##    predicted_depth.unsqueeze(1),
-    ##    size=image.size[::-1],
-    ##    mode="bicubic",
-    ##    align_corners=False,
-    ##)
-
-    ### visualize the prediction
-    ##edput = prediction.squeeze().cpu().numpy()
-    ##formatted = (edput * 255 / np.max(edput)).astype("uint8")
-    ##depth = Image.fromarray(formatted)
-    ##depth = Image.open(depth).resize((512, 512))
-    ##depth = depth.convert("RGB")
-    ##depth = np.array(depth)
-    ##depth = depth[:, :, None]
-    ##depth = np.concatenate([depth, depth, depth], axis=2)
-    ##detected_map = torch.from_numpy(depth).float() / 255.0
-    ##hint = detected_map.permute(2, 0, 1)
-    ##hint = depth
-    ##image = depth_estimator(image)['predicted_depth'][0]
-    ##image = image.numpy()
-    ##image_depth = image.copy()
-    ##image_depth -= np.min(image_depth)
-    ##image_depth /= np.max(image_depth)
-    ##bg_threhold = 0.4
-    ##x = cv2.Sobel(image, cv2.CV_32F, 1, 0, ksize=3)
-    ##x[image_depth < bg_threhold] = 0
-    ##y = cv2.Sobel(image, cv2.CV_32F, 0, 1, ksize=3)
-    ##y[image_depth < bg_threhold] = 0
-    ##z = np.ones_like(x) * np.pi * 2.0
-    ##image = np.stack([x, y, z], axis=2)
-    ##image /= np.sum(image ** 2.0, axis=2, keepdims=True) ** 0.5
-    ##image = (image * 127.5 + 127.5).clip(0, 255).astype(np.uint8)
-    ##image = np.array(Image.fromarray(image))
-    ##hint = torch.from_numpy(image).float() / 255.0
+    
     return hint
 
 def plex(prompt,goof):
-    ##goof = Image.open(goof).resize((512, 512))
+
     goof = load_image(goof)
     goof = goof.convert("RGB")
-    ##goof.thumbnail((512, 512))
-    ##hint = make_hint(goof).unsqueeze(0).to("cpu")
+
     hint = make_hint(goof, depth_estimator).unsqueeze(0).to("cpu")
     negative_prior_prompt = "lowres,text,bad quality,jpeg artifacts,ugly,bad face,extra fingers,blurry,bad anatomy,extra limbs,fused fingers,long neck,watermark,signature"
     image_emb, zero_image_emb = pipe_prior(prompt=prompt, negative_prompt=negative_prior_prompt, num_inference_steps=5,generator=generator).to_tuple()