Update app.py

app.py

@@ -21,7 +21,7 @@ from insightface.app import FaceAnalysis
 from style_template import styles
 from pipeline_stable_diffusion_xl_instantid_full import StableDiffusionXLInstantIDPipeline, draw_kps
 
-# from controlnet_aux import OpenposeDetector
+from controlnet_aux import OpenposeDetector
 
 import gradio as gr
 
@@ -58,7 +58,7 @@ app = FaceAnalysis(
 )
 app.prepare(ctx_id=0, det_size=(640, 640))
 
-# openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
+openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
 
 depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_vitl14').to(device).eval()
 
@@ -86,13 +86,13 @@ controlnet_identitynet = ControlNetModel.from_pretrained(
 )
 
 # controlnet-pose/canny/depth
-# controlnet_pose_model = "thibaud/controlnet-openpose-sdxl-1.0"
+controlnet_pose_model = "thibaud/controlnet-openpose-sdxl-1.0"
 controlnet_canny_model = "diffusers/controlnet-canny-sdxl-1.0"
 controlnet_depth_model = "diffusers/controlnet-depth-sdxl-1.0-small"
 
-# controlnet_pose = ControlNetModel.from_pretrained(
-#     controlnet_pose_model, torch_dtype=dtype
-# ).to(device)
+controlnet_pose = ControlNetModel.from_pretrained(
+    controlnet_pose_model, torch_dtype=dtype
+).to(device)
 controlnet_canny = ControlNetModel.from_pretrained(
     controlnet_canny_model, torch_dtype=dtype
 ).to(device)
@@ -127,12 +127,12 @@ def get_canny_image(image, t1=100, t2=200):
     return Image.fromarray(edges, "L")
 
 controlnet_map = {
-    # "pose": controlnet_pose,
+    "pose": controlnet_pose,
     "canny": controlnet_canny,
     "depth": controlnet_depth,
 }
 controlnet_map_fn = {
-    # "pose": openpose,
+    "pose": openpose,
     "canny": get_canny_image,
     "depth": get_depth_map,
 }
@@ -230,10 +230,10 @@ def run_for_examples(face_file, pose_file, prompt, style, negative_prompt):
         20,  # num_steps
         0.8,  # identitynet_strength_ratio
         0.8,  # adapter_strength_ratio
-        # 0.4,  # pose_strength
+        0.4,  # pose_strength
         0.3,  # canny_strength
         0.5,  # depth_strength
-        ["depth", "canny"],  # controlnet_selection
+        ["pose", "canny"],  # controlnet_selection
         5.0,  # guidance_scale
         42,  # seed
         "EulerDiscreteScheduler",  # scheduler
@@ -294,7 +294,7 @@ def generate_image(
     num_steps,
     identitynet_strength_ratio,
     adapter_strength_ratio,
-    # pose_strength,
+    pose_strength,
     canny_strength,
     depth_strength,
     controlnet_selection,
@@ -383,7 +383,7 @@ def generate_image(
 
     if len(controlnet_selection) > 0:
         controlnet_scales = {
-            # "pose": pose_strength,
+            "pose": pose_strength,
             "canny": canny_strength,
             "depth": depth_strength,
         }
@@ -432,9 +432,7 @@ title = r"""
 
 description = r"""
 <b>Official 🤗 Gradio demo</b> for <a href='https://github.com/InstantID/InstantID' target='_blank'><b>InstantID: Zero-shot Identity-Preserving Generation in Seconds</b></a>.<br>
-
 We are organizing a Spring Festival event with HuggingFace from 2.7 to 2.25, and you can now generate pictures of Spring Festival costumes. Happy Dragon Year 🐲 ! Share the joy with your family.<br>
-
 How to use:<br>
 1. Upload an image with a face. For images with multiple faces, we will only detect the largest face. Ensure the face is not too small and is clearly visible without significant obstructions or blurring.
 2. (Optional) You can upload another image as a reference for the face pose. If you don't, we will use the first detected face image to extract facial landmarks. If you use a cropped face at step 1, it is recommended to upload it to define a new face pose.
@@ -526,16 +524,16 @@ with gr.Blocks(css=css) as demo:
             )
             with gr.Accordion("Controlnet"):
                 controlnet_selection = gr.CheckboxGroup(
-                    ["canny", "depth"], label="Controlnet", value=["canny"],
+                    ["pose", "canny", "depth"], label="Controlnet", value=["pose"],
                     info="Use pose for skeleton inference, canny for edge detection, and depth for depth map estimation. You can try all three to control the generation process"
                 )
-                # pose_strength = gr.Slider(
-                #     label="Pose strength",
-                #     minimum=0,
-                #     maximum=1.5,
-                #     step=0.05,
-                #     value=0.40,
-                # )
+                pose_strength = gr.Slider(
+                    label="Pose strength",
+                    minimum=0,
+                    maximum=1.5,
+                    step=0.05,
+                    value=0.40,
+                )
                 canny_strength = gr.Slider(
                     label="Canny strength",
                     minimum=0,
@@ -619,7 +617,7 @@ with gr.Blocks(css=css) as demo:
                 num_steps,
                 identitynet_strength_ratio,
                 adapter_strength_ratio,
-                # pose_strength,
+                pose_strength,
                 canny_strength,
                 depth_strength,
                 controlnet_selection,
@@ -650,4 +648,4 @@ with gr.Blocks(css=css) as demo:
     gr.Markdown(article)
 
 demo.queue(api_open=False)
-demo.launch()
+demo.launch()