From d616c513c9b85a89b952da839f987db03f3561f6 Mon Sep 17 00:00:00 2001 From: GhoulBoii Date: Thu, 24 Oct 2024 00:24:42 +0530 Subject: [PATCH] feat(): adding mouth masking --- modules/globals.py | 3 + modules/processors/frame/face_swapper.py | 161 ++++++++++++++++++----- modules/ui.py | 77 +++++++++++ 3 files changed, 208 insertions(+), 33 deletions(-) diff --git a/modules/globals.py b/modules/globals.py index cffae16..9618a61 100644 --- a/modules/globals.py +++ b/modules/globals.py @@ -36,3 +36,6 @@ fp_ui: Dict[str, bool] = {"face_enhancer": False} camera_input_combobox = None webcam_preview_running = False show_fps = False +mouth_mask = False +show_mouth_mask_box = False +mouth_mask_switch_preview = None diff --git a/modules/processors/frame/face_swapper.py b/modules/processors/frame/face_swapper.py index 6fd0760..4fb29de 100644 --- a/modules/processors/frame/face_swapper.py +++ b/modules/processors/frame/face_swapper.py @@ -1,5 +1,6 @@ -from typing import Any, List +from typing import Any, List, Tuple import cv2 +import numpy as np import insightface import threading @@ -8,29 +9,48 @@ import modules.processors.frame.core from modules.core import update_status from modules.face_analyser import get_one_face, get_many_faces, default_source_face from modules.typing import Face, Frame -from modules.utilities import conditional_download, resolve_relative_path, is_image, is_video +from modules.utilities import ( + conditional_download, + resolve_relative_path, + is_image, + is_video, +) from modules.cluster_analysis import find_closest_centroid FACE_SWAPPER = None THREAD_LOCK = threading.Lock() -NAME = 'DLC.FACE-SWAPPER' +NAME = "DLC.FACE-SWAPPER" + +# Add mouth landmarks indices for masking +MOUTH_LANDMARKS = list( + range(46, 68) +) # Common indices for mouth landmarks in facial detection def pre_check() -> bool: - download_directory_path = resolve_relative_path('../models') - conditional_download(download_directory_path, ['https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx']) + download_directory_path = resolve_relative_path("../models") + conditional_download( + download_directory_path, + [ + "https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx" + ], + ) return True def pre_start() -> bool: if not modules.globals.map_faces and not is_image(modules.globals.source_path): - update_status('Select an image for source path.', NAME) + update_status("Select an image for source path.", NAME) return False - elif not modules.globals.map_faces and not get_one_face(cv2.imread(modules.globals.source_path)): - update_status('No face in source path detected.', NAME) + elif not modules.globals.map_faces and not get_one_face( + cv2.imread(modules.globals.source_path) + ): + update_status("No face in source path detected.", NAME) return False - if not is_image(modules.globals.target_path) and not is_video(modules.globals.target_path): - update_status('Select an image or video for target path.', NAME) + if not is_image(modules.globals.target_path) and not is_video( + modules.globals.target_path + ): + update_status("Select an image or video for target path.", NAME) return False return True @@ -40,20 +60,60 @@ def get_face_swapper() -> Any: with THREAD_LOCK: if FACE_SWAPPER is None: - model_path = resolve_relative_path('../models/inswapper_128_fp16.onnx') - FACE_SWAPPER = insightface.model_zoo.get_model(model_path, providers=modules.globals.execution_providers) + model_path = resolve_relative_path("../models/inswapper_128_fp16.onnx") + FACE_SWAPPER = insightface.model_zoo.get_model( + model_path, providers=modules.globals.execution_providers + ) return FACE_SWAPPER +def create_mouth_mask(face: Face, frame_shape: Tuple[int, int]) -> np.ndarray: + """Create a mask for the mouth region""" + mask = np.zeros(frame_shape[:2], dtype=np.uint8) + + # Get mouth landmarks from the face + landmarks = face.kps + mouth_points = landmarks[MOUTH_LANDMARKS].astype(np.int32) + + # Create a polygon around the mouth region + cv2.fillPoly(mask, [mouth_points], 255) + + # Dilate the mask slightly to ensure smooth blending + kernel = np.ones((5, 5), np.uint8) + mask = cv2.dilate(mask, kernel, iterations=2) + + # Blur the mask edges + mask = cv2.GaussianBlur(mask, (15, 15), 10) + + return mask + + +def blend_with_mask( + swapped_frame: Frame, original_frame: Frame, mask: np.ndarray +) -> Frame: + """Blend the swapped face with the original frame using the mouth mask""" + mask_3channel = cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR) / 255.0 + + # Blend the images based on the mask + blended = swapped_frame * (1 - mask_3channel) + original_frame * mask_3channel + return blended.astype(np.uint8) + + def swap_face(source_face: Face, target_face: Face, temp_frame: Frame) -> Frame: - return get_face_swapper().get(temp_frame, target_face, source_face, paste_back=True) + # Store the original frame for mouth preservation + original_frame = temp_frame.copy() + + # Perform the face swap + swapped_frame = get_face_swapper().get( + temp_frame, target_face, source_face, paste_back=True + ) def process_frame(source_face: Face, temp_frame: Frame) -> Frame: # Ensure the frame is in RGB format if color correction is enabled if modules.globals.color_correction: temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB) - + if modules.globals.many_faces: many_faces = get_many_faces(temp_frame) if many_faces: @@ -71,34 +131,42 @@ def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame: if modules.globals.many_faces: source_face = default_source_face() for map in modules.globals.souce_target_map: - target_face = map['target']['face'] + target_face = map["target"]["face"] temp_frame = swap_face(source_face, target_face, temp_frame) elif not modules.globals.many_faces: for map in modules.globals.souce_target_map: if "source" in map: - source_face = map['source']['face'] - target_face = map['target']['face'] + source_face = map["source"]["face"] + target_face = map["target"]["face"] temp_frame = swap_face(source_face, target_face, temp_frame) elif is_video(modules.globals.target_path): if modules.globals.many_faces: source_face = default_source_face() for map in modules.globals.souce_target_map: - target_frame = [f for f in map['target_faces_in_frame'] if f['location'] == temp_frame_path] + target_frame = [ + f + for f in map["target_faces_in_frame"] + if f["location"] == temp_frame_path + ] for frame in target_frame: - for target_face in frame['faces']: + for target_face in frame["faces"]: temp_frame = swap_face(source_face, target_face, temp_frame) elif not modules.globals.many_faces: for map in modules.globals.souce_target_map: if "source" in map: - target_frame = [f for f in map['target_faces_in_frame'] if f['location'] == temp_frame_path] - source_face = map['source']['face'] + target_frame = [ + f + for f in map["target_faces_in_frame"] + if f["location"] == temp_frame_path + ] + source_face = map["source"]["face"] for frame in target_frame: - for target_face in frame['faces']: + for target_face in frame["faces"]: temp_frame = swap_face(source_face, target_face, temp_frame) else: detected_faces = get_many_faces(temp_frame) @@ -110,25 +178,46 @@ def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame: elif not modules.globals.many_faces: if detected_faces: - if len(detected_faces) <= len(modules.globals.simple_map['target_embeddings']): + if len(detected_faces) <= len( + modules.globals.simple_map["target_embeddings"] + ): for detected_face in detected_faces: - closest_centroid_index, _ = find_closest_centroid(modules.globals.simple_map['target_embeddings'], detected_face.normed_embedding) + closest_centroid_index, _ = find_closest_centroid( + modules.globals.simple_map["target_embeddings"], + detected_face.normed_embedding, + ) - temp_frame = swap_face(modules.globals.simple_map['source_faces'][closest_centroid_index], detected_face, temp_frame) + temp_frame = swap_face( + modules.globals.simple_map["source_faces"][ + closest_centroid_index + ], + detected_face, + temp_frame, + ) else: detected_faces_centroids = [] for face in detected_faces: - detected_faces_centroids.append(face.normed_embedding) + detected_faces_centroids.append(face.normed_embedding) i = 0 - for target_embedding in modules.globals.simple_map['target_embeddings']: - closest_centroid_index, _ = find_closest_centroid(detected_faces_centroids, target_embedding) + for target_embedding in modules.globals.simple_map[ + "target_embeddings" + ]: + closest_centroid_index, _ = find_closest_centroid( + detected_faces_centroids, target_embedding + ) - temp_frame = swap_face(modules.globals.simple_map['source_faces'][i], detected_faces[closest_centroid_index], temp_frame) + temp_frame = swap_face( + modules.globals.simple_map["source_faces"][i], + detected_faces[closest_centroid_index], + temp_frame, + ) i += 1 return temp_frame -def process_frames(source_path: str, temp_frame_paths: List[str], progress: Any = None) -> None: +def process_frames( + source_path: str, temp_frame_paths: List[str], progress: Any = None +) -> None: if not modules.globals.map_faces: source_face = get_one_face(cv2.imread(source_path)) for temp_frame_path in temp_frame_paths: @@ -162,7 +251,9 @@ def process_image(source_path: str, target_path: str, output_path: str) -> None: cv2.imwrite(output_path, result) else: if modules.globals.many_faces: - update_status('Many faces enabled. Using first source image. Progressing...', NAME) + update_status( + "Many faces enabled. Using first source image. Progressing...", NAME + ) target_frame = cv2.imread(output_path) result = process_frame_v2(target_frame) cv2.imwrite(output_path, result) @@ -170,5 +261,9 @@ def process_image(source_path: str, target_path: str, output_path: str) -> None: def process_video(source_path: str, temp_frame_paths: List[str]) -> None: if modules.globals.map_faces and modules.globals.many_faces: - update_status('Many faces enabled. Using first source image. Progressing...', NAME) - modules.processors.frame.core.process_video(source_path, temp_frame_paths, process_frames) + update_status( + "Many faces enabled. Using first source image. Progressing...", NAME + ) + modules.processors.frame.core.process_video( + source_path, temp_frame_paths, process_frames + ) diff --git a/modules/ui.py b/modules/ui.py index bbfebf1..69ef04a 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -59,6 +59,8 @@ RECENT_DIRECTORY_SOURCE = None RECENT_DIRECTORY_TARGET = None RECENT_DIRECTORY_OUTPUT = None +BLUR_SIZE = 1 + preview_label = None preview_slider = None source_label = None @@ -317,6 +319,47 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C live_button.place(relx=0.65, rely=0.86, relwidth=0.2, relheight=0.05) # --- End Camera Selection --- + show_mouth_mask_var = ctk.BooleanVar(value=modules.globals.show_mouth_mask_box) + show_mouth_mask_switch = ctk.CTkSwitch( + root, + text="Show Mouth Mask Box", + variable=show_mouth_mask_var, + cursor="hand2", + command=lambda: setattr( + modules.globals, "show_mouth_mask_box", show_mouth_mask_var.get() + ), + progress_color="#3a7ebf", + font=("Roboto", 14, "bold"), + ) + show_mouth_mask_switch.pack(pady=5, anchor="w") + + # Create frame for mouth mask + mouth_mask_frame = ctk.CTkFrame( + root, fg_color="#2a2d2e", border_width=1, border_color="grey" + ) + mouth_mask_frame.pack(pady=5, anchor="w", fill="x") + + # Create a shared BooleanVar in modules.globals + if not hasattr(modules.globals, "mouth_mask_var"): + modules.globals.mouth_mask_var = ctk.BooleanVar( + value=modules.globals.mouth_mask + ) + + # Mouth mask switch + mouth_mask_switch = ctk.CTkSwitch( + mouth_mask_frame, + text="Mouth Mask", + variable=modules.globals.mouth_mask_var, + cursor="hand2", + command=toggle_mouthmask, + progress_color="#3a7ebf", + font=("Roboto", 14, "bold"), + ) + mouth_mask_switch.pack(pady=5, anchor="w") + + # Store the switch in modules.globals for access from create_preview + modules.globals.mouth_mask_switch_root = mouth_mask_switch + status_label = ctk.CTkLabel(root, text=None, justify="center") status_label.place(relx=0.1, rely=0.9, relwidth=0.8) @@ -478,6 +521,29 @@ def update_popup_source( return map +def toggle_mouthmask(): + """ + Toggle the mouth mask state and synchronize all UI switches. + Updates both the global state and any existing switch controls. + """ + is_mouthmask = modules.globals.mouth_mask_var.get() + modules.globals.mouth_mask = is_mouthmask + + # Update root window switch if it exists + if hasattr(modules.globals, "mouth_mask_switch_root"): + if is_mouthmask: + modules.globals.mouth_mask_switch_root.select() + else: + modules.globals.mouth_mask_switch_root.deselect() + + # Update preview window switch if it exists + if hasattr(modules.globals, "mouth_mask_switch_preview"): + if is_mouthmask: + modules.globals.mouth_mask_switch_preview.select() + else: + modules.globals.mouth_mask_switch_preview.deselect() + + def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel: global preview_label, preview_slider @@ -494,6 +560,17 @@ def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel: preview_slider = ctk.CTkSlider( preview, from_=0, to=0, command=lambda frame_value: update_preview(frame_value) ) + mouth_mask_switch_preview = ctk.CTkSwitch( + preview, + text="Mouth Mask", + variable=modules.globals.mouth_mask_var, + cursor="hand2", + command=toggle_mouthmask, + ) + mouth_mask_switch_preview.pack(side="left", padx=5, pady=5) + + # Store the switch in modules.globals for access from create_root + modules.globals.mouth_mask_switch_preview = mouth_mask_switch_preview return preview