remove input resize

main.py

@@ -283,7 +283,7 @@ def prepare_inputs_train(images, bg_remove, dwpose, rembg_session):
     return in_img, in_pose, train_imgs, train_poses
         
 
-def prepare_inputs_inference(in_img, in_vid, fps, dwpose, rembg_session, bg_remove, resize='target', is_app=False):
+def prepare_inputs_inference(in_img, in_vid, fps, dwpose, rembg_session, bg_remove, resize_inputs, is_app=False):
     progress=gr.Progress(track_tqdm=True)
 
     print("prepare_inputs_inference")
@@ -334,7 +334,7 @@ def prepare_inputs_inference(in_img, in_vid, fps, dwpose, rembg_session, bg_remo
         
     target_poses_cropped = []
     for tpose in target_poses:
-        if resize=='target':
+        if resize_inputs:
             tpose = tpose.crop((max_left, max_top, max_right, max_bottom))
             tpose = ImageOps.expand(tpose, border=int(tpose.width*0.2), fill=(0,0,0))
             
@@ -348,11 +348,11 @@ def prepare_inputs_inference(in_img, in_vid, fps, dwpose, rembg_session, bg_remo
     return in_img, target_poses_cropped, in_pose, target_poses_coords, frames
 
 
-def prepare_inputs(images, in_vid, fps, bg_remove, dwpose, rembg_session, resize='target', is_app=False):
+def prepare_inputs(images, in_vid, fps, bg_remove, dwpose, rembg_session, resize_inputs, is_app=False):
     
     in_img, in_pose, train_imgs, train_poses = prepare_inputs_train(images, bg_remove, dwpose, rembg_session)
     
-    in_img, target_poses_cropped, _, _, _ = prepare_inputs_inference(in_img, in_vid, fps, dwpose, rembg_session, bg_remove, resize, is_app)
+    in_img, target_poses_cropped, _, _, _ = prepare_inputs_inference(in_img, in_vid, fps, dwpose, rembg_session, bg_remove, resize_inputs, is_app)
     
     
     return in_img, in_pose, train_imgs, train_poses, target_poses_cropped
@@ -1087,11 +1087,7 @@ def run(images, video_path, train_steps=100, inference_steps=10, fps=12, bg_remo
     dwpose, rembg_session, pcdms_model, noise_scheduler, image_encoder_p, image_encoder_g, vae, unet = load_models()
     
     print("==== Pose Detection ====")
-    if resize_inputs:
-        resize = 'target'
-    else:
-        resize = 'none'
-    in_img, in_pose, train_imgs, train_poses, target_poses = prepare_inputs(images, video_path, fps, bg_remove, dwpose, rembg_session, resize=resize, is_app=is_app)
+    in_img, in_pose, train_imgs, train_poses, target_poses = prepare_inputs(images, video_path, fps, bg_remove, dwpose, rembg_session, resize_inputs, is_app=is_app)
     
     if save_model:
         train("fine_tuned_pcdms", in_img, in_pose, train_imgs, train_poses, train_steps, pcdms_model, noise_scheduler, image_encoder_p, image_encoder_g, vae, unet, finetune, is_app)
@@ -1138,7 +1134,7 @@ def run_inference(images, video_path, train_steps=100, inference_steps=10, fps=1
     images = [img[0] for img in images]
     in_img = images[0]
 
-    in_img, target_poses, in_pose, target_poses_coords, orig_frames = prepare_inputs_inference(in_img, video_path, fps, dwpose, rembg_session, bg_remove, 'target', is_app)
+    in_img, target_poses, in_pose, target_poses_coords, orig_frames = prepare_inputs_inference(in_img, video_path, fps, dwpose, rembg_session, bg_remove, resize_inputs, is_app)
     
     results = inference(modelId, in_img, in_pose, target_poses, inference_steps, None, vae, unet, image_encoder_p, is_app)
     #urls = save_temp_imgs(results)