RealVisXL

app.py

@@ -1,3 +1,4 @@
+from huggingface_hub import hf_hub_download
 import math
 import random
 
@@ -22,18 +23,20 @@ STYLE_NAMES = list(styles.keys())
 DEFAULT_STYLE_NAME = "Watercolor"
 
 # download checkpoints
-from huggingface_hub import hf_hub_download
 
-hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/config.json", local_dir="./checkpoints")
+hf_hub_download(repo_id="InstantX/InstantID",
+                filename="ControlNetModel/config.json", local_dir="./checkpoints")
 hf_hub_download(
     repo_id="InstantX/InstantID",
     filename="ControlNetModel/diffusion_pytorch_model.safetensors",
     local_dir="./checkpoints",
 )
-hf_hub_download(repo_id="InstantX/InstantID", filename="ip-adapter.bin", local_dir="./checkpoints")
+hf_hub_download(repo_id="InstantX/InstantID",
+                filename="ip-adapter.bin", local_dir="./checkpoints")
 
 # Load face encoder
-app = FaceAnalysis(name="antelopev2", root="./", providers=["CPUExecutionProvider"])
+app = FaceAnalysis(name="antelopev2", root="./",
+                   providers=["CPUExecutionProvider"])
 app.prepare(ctx_id=0, det_size=(640, 640))
 
 # Path to InstantID models
@@ -41,9 +44,10 @@ face_adapter = "./checkpoints/ip-adapter.bin"
 controlnet_path = "./checkpoints/ControlNetModel"
 
 # Load pipeline
-controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)
+controlnet = ControlNetModel.from_pretrained(
+    controlnet_path, torch_dtype=torch.float16)
 
-base_model_path = "wangqixun/YamerMIX_v8"
+base_model_path = "SG161222/RealVisXL_V3.0"
 
 pipe = StableDiffusionXLInstantIDPipeline.from_pretrained(
     base_model_path,
@@ -133,7 +137,8 @@ def draw_kps(image_pil, kps, color_list=[(255, 0, 0), (0, 255, 0), (0, 0, 255),
         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
+            (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)
@@ -163,16 +168,20 @@ def resize_img(
         ratio = min_side / min(h, w)
         w, h = round(ratio * w), round(ratio * h)
         ratio = max_side / max(h, w)
-        input_image = input_image.resize([round(ratio * w), round(ratio * h)], mode)
-        w_resize_new = (round(ratio * w) // base_pixel_number) * base_pixel_number
-        h_resize_new = (round(ratio * h) // base_pixel_number) * base_pixel_number
+        input_image = input_image.resize(
+            [round(ratio * w), round(ratio * h)], mode)
+        w_resize_new = (round(ratio * w) // base_pixel_number) * \
+            base_pixel_number
+        h_resize_new = (round(ratio * h) // base_pixel_number) * \
+            base_pixel_number
     input_image = input_image.resize([w_resize_new, h_resize_new], mode)
 
     if pad_to_max_side:
         res = np.ones([max_side, max_side, 3], dtype=np.uint8) * 255
         offset_x = (max_side - w_resize_new) // 2
         offset_y = (max_side - h_resize_new) // 2
-        res[offset_y : offset_y + h_resize_new, offset_x : offset_x + w_resize_new] = np.array(input_image)
+        res[offset_y: offset_y + h_resize_new, offset_x: offset_x +
+            w_resize_new] = np.array(input_image)
         input_image = Image.fromarray(res)
     return input_image
 
@@ -184,7 +193,8 @@ def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str
 
 def check_input_image(face_image):
     if face_image is None:
-        raise gr.Error("Cannot find any input face image! Please upload the face image")
+        raise gr.Error(
+            "Cannot find any input face image! Please upload the face image")
 
 
 @spaces.GPU
@@ -217,13 +227,15 @@ def generate_image(
     face_info = app.get(face_image_cv2)
 
     if len(face_info) == 0:
-        raise gr.Error("Cannot find any face in the image! Please upload another person image")
+        raise gr.Error(
+            "Cannot find any face in the image! Please upload another person image")
 
     face_info = sorted(face_info, key=lambda x: (x["bbox"][2] - x["bbox"][0]) * x["bbox"][3] - x["bbox"][1])[
         -1
     ]  # only use the maximum face
     face_emb = face_info["embedding"]
-    face_kps = draw_kps(convert_from_cv2_to_image(face_image_cv2), face_info["kps"])
+    face_kps = draw_kps(convert_from_cv2_to_image(
+        face_image_cv2), face_info["kps"])
 
     if pose_image_path is not None:
         pose_image = load_image(pose_image_path)
@@ -233,7 +245,8 @@ def generate_image(
         face_info = app.get(pose_image_cv2)
 
         if len(face_info) == 0:
-            raise gr.Error("Cannot find any face in the reference image! Please upload another person image")
+            raise gr.Error(
+                "Cannot find any face in the reference image! Please upload another person image")
 
         face_info = face_info[-1]
         face_kps = draw_kps(pose_image, face_info["kps"])
@@ -272,7 +285,7 @@ def generate_image(
     return images[0], gr.update(visible=True)
 
 
-### Description
+# Description
 title = r"""
 <h1 align="center">InstantID: Zero-shot Identity-Preserving Generation in Seconds</h1>
 """
@@ -325,10 +338,12 @@ with gr.Blocks(css=css) as demo:
     with gr.Row():
         with gr.Column():
             # upload face image
-            face_file = gr.Image(label="Upload a photo of your face", type="filepath")
+            face_file = gr.Image(
+                label="Upload a photo of your face", type="filepath")
 
             # optional: upload a reference pose image
-            pose_file = gr.Image(label="Upload a reference pose image (optional)", type="filepath")
+            pose_file = gr.Image(
+                label="Upload a reference pose image (optional)", type="filepath")
 
             # prompt
             prompt = gr.Textbox(
@@ -340,7 +355,8 @@ with gr.Blocks(css=css) as demo:
 
             submit = gr.Button("Submit", variant="primary")
 
-            style = gr.Dropdown(label="Style template", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
+            style = gr.Dropdown(label="Style template",
+                                choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
 
             # strength
             identitynet_strength_ratio = gr.Slider(
@@ -385,12 +401,15 @@ with gr.Blocks(css=css) as demo:
                     step=1,
                     value=42,
                 )
-                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-                enhance_face_region = gr.Checkbox(label="Enhance non-face region", value=True)
+                randomize_seed = gr.Checkbox(
+                    label="Randomize seed", value=True)
+                enhance_face_region = gr.Checkbox(
+                    label="Enhance non-face region", value=True)
 
         with gr.Column():
             output_image = gr.Image(label="Generated Image")
-            usage_tips = gr.Markdown(label="Usage tips of InstantID", value=tips, visible=False)
+            usage_tips = gr.Markdown(
+                label="Usage tips of InstantID", value=tips, visible=False)
 
         submit.click(
             fn=remove_tips,