size 512, rewrite fucntion

handler.py

@@ -47,8 +47,8 @@ class EndpointHandler():
 
         transform = Compose([
             Resize(
-                width=518,
-                height=518,
+                width=512,
+                height=512,
                 resize_target=False,
                 keep_aspect_ratio=True,
                 ensure_multiple_of=14,
@@ -146,7 +146,7 @@ class EndpointHandler():
         }
         
         self.app = FaceAnalysis(name="buffalo_l", root="./", providers=["CPUExecutionProvider"])
-        self.app.prepare(ctx_id=0, det_size=(640, 640))
+        self.app.prepare(ctx_id=0, det_size=(512, 512))
         self.generator = torch.Generator(device=device.type).manual_seed(3)
 
 
@@ -181,8 +181,14 @@ class EndpointHandler():
         num_inference_steps = data.pop("num_inference_steps", 5)
         guidance_scale = data.pop("guidance_scale", 1.5)
         negative_prompt = data.pop("negative_prompt", default_negative_prompt)
-        face_image_path = data.pop("face_image_path", "https://i.ibb.co/SKg69dD/kaifu-resize.png")
-        pose_image_path = data.pop("pose_image_path", "https://i.ibb.co/ZSrQ8ZJ/pose.jpg")
+
+        # 1024px
+        # face_image_path = data.pop("face_image_path", "https://i.ibb.co/SKg69dD/kaifu-resize.png")
+        # pose_image_path = data.pop("pose_image_path", "https://i.ibb.co/ZSrQ8ZJ/pose.jpg")
+        # 512px
+        face_image_path = "https://i.ibb.co/5Rsrd2d/kaifu-resize-1.png"
+        pose_image_path = "https://i.ibb.co/9bP9tMb/pose-2-1.jpg"
+        
         
         adapter_strength_ratio = 0.8
         

pipeline_stable_diffusion_xl_instantid_full.py

@@ -469,34 +469,33 @@ class LongPromptWeight(object):
         prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
         return prompt_embeds
 
-def draw_kps(image_pil, kps, color_list=[(255,0,0), (0,255,0), (0,0,255), (255,255,0), (255,0,255)]):
-    
-    stickwidth = 4
-    limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
-    kps = np.array(kps)
-
-    w, h = image_pil.size
-    out_img = np.zeros([h, w, 3])
-
-    for i in range(len(limbSeq)):
-        index = limbSeq[i]
-        color = color_list[index[0]]
-
-        x = kps[index][:, 0]
-        y = kps[index][:, 1]
-        length = ((x[0] - x[1]) ** 2 + (y[0] - y[1]) ** 2) ** 0.5
-        angle = math.degrees(math.atan2(y[0] - y[1], x[0] - x[1]))
-        polygon = cv2.ellipse2Poly((int(np.mean(x)), int(np.mean(y))), (int(length / 2), stickwidth), int(angle), 0, 360, 1)
-        out_img = cv2.fillConvexPoly(out_img.copy(), polygon, color)
-    out_img = (out_img * 0.6).astype(np.uint8)
-
-    for idx_kp, kp in enumerate(kps):
-        color = color_list[idx_kp]
-        x, y = kp
-        out_img = cv2.circle(out_img.copy(), (int(x), int(y)), 10, color, -1)
-
-    out_img_pil = PIL.Image.fromarray(out_img.astype(np.uint8))
-    return out_img_pil
+    def draw_kps_optimized(image_pil, kps, color_list=[(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255)]):
+        stickwidth = 4
+        limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
+        kps = np.array(kps)
+
+        w, h = image_pil.size
+        out_img = np.zeros([h, w, 3], dtype=np.uint8) 
+
+        for i, (start, end) in enumerate(limbSeq):
+            color = color_list[i % len(color_list)] 
+
+            x = kps[[start, end], 0]
+            y = kps[[start, end], 1]
+
+            center = tuple(np.round(np.mean([x, y], axis=1)).astype(int))
+            length = int(np.hypot(x[0] - x[1], y[0] - y[1]) / 2)
+            angle = int(np.degrees(np.arctan2(y[0] - y[1], x[0] - x[1])))
+
+            polygon = cv2.ellipse2Poly(center, (length, stickwidth), angle, 0, 360, 1)
+            cv2.fillConvexPoly(out_img, polygon, color)
+
+        for idx_kp, (x, y) in enumerate(kps):
+            color = color_list[idx_kp % len(color_list)]  
+            cv2.circle(out_img, (int(x), int(y)), 10, color, thickness=-1)
+
+        out_img_pil = PIL.Image.fromarray(out_img)
+        return out_img_pil
     
 class StableDiffusionXLInstantIDPipeline(StableDiffusionXLControlNetPipeline):
     
@@ -527,7 +526,7 @@ class StableDiffusionXLInstantIDPipeline(StableDiffusionXLControlNetPipeline):
     def set_image_proj_model(self, model_ckpt, image_emb_dim=512, num_tokens=16):
         
         image_proj_model = Resampler(
-            dim=1280,
+            dim=512,
             depth=4,
             dim_head=64,
             heads=20,