Merge 2e617c9401 into 28109e93bb
rehanbgmi
GitHub
commit
ff0608292d
66
README.md
66
README.md
|
|
@ -150,22 +150,64 @@ pip install -r requirements.txt
|
|||
|
||||
**For macOS:**
|
||||
|
||||
Apple Silicon (M1/M2/M3) requires specific setup:
|
||||
For a streamlined setup on macOS, use the provided shell scripts:
|
||||
|
||||
```bash
|
||||
# Install Python 3.10 (specific version is important)
|
||||
brew install python@3.10
|
||||
1. **Make scripts executable:**
|
||||
Open your terminal, navigate to the cloned `Deep-Live-Cam` directory, and run:
|
||||
```bash
|
||||
chmod +x setup_mac.sh
|
||||
chmod +x run_mac*.sh
|
||||
```
|
||||
|
||||
# Install tkinter package (required for the GUI)
|
||||
brew install python-tk@3.10
|
||||
2. **Run the setup script:**
|
||||
This will check for Python 3.9+, ffmpeg, create a virtual environment (`.venv`), and install required Python packages.
|
||||
```bash
|
||||
./setup_mac.sh
|
||||
```
|
||||
If you encounter issues with specific packages during `pip install` (especially for libraries that compile C code, like some image processing libraries), you might need to install system libraries via Homebrew (e.g., `brew install jpeg libtiff ...`) or ensure Xcode Command Line Tools are installed (`xcode-select --install`).
|
||||
|
||||
# Create and activate virtual environment with Python 3.10
|
||||
python3.10 -m venv venv
|
||||
source venv/bin/activate
|
||||
3. **Activate the virtual environment (for manual runs):**
|
||||
After setup, if you want to run commands manually or use developer tools from your terminal session:
|
||||
```bash
|
||||
source .venv/bin/activate
|
||||
```
|
||||
(To deactivate, simply type `deactivate` in the terminal.)
|
||||
|
||||
# Install dependencies
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
4. **Run the application:**
|
||||
Use the provided run scripts for convenience. These scripts automatically activate the virtual environment.
|
||||
* `./run_mac.sh`: Runs the application with the CPU execution provider by default. This is a good starting point.
|
||||
* `./run_mac_cpu.sh`: Explicitly uses the CPU execution provider.
|
||||
* `./run_mac_coreml.sh`: Attempts to use the CoreML execution provider for potential hardware acceleration on Apple Silicon and Intel Macs.
|
||||
* `./run_mac_mps.sh`: Attempts to use the MPS (Metal Performance Shaders) execution provider, primarily for Apple Silicon Macs.
|
||||
|
||||
Example of running with specific source/target arguments:
|
||||
```bash
|
||||
./run_mac.sh --source path/to/your_face.jpg --target path/to/video.mp4
|
||||
```
|
||||
Or, to simply launch the UI:
|
||||
```bash
|
||||
./run_mac.sh
|
||||
```
|
||||
|
||||
**Important Notes for macOS GPU Acceleration (CoreML/MPS):**
|
||||
|
||||
* The `setup_mac.sh` script installs packages from `requirements.txt`, which typically includes a general CPU-based version of `onnxruntime`.
|
||||
* For optimal performance on Apple Silicon (M1/M2/M3) or specific GPU acceleration, you might need to install a different `onnxruntime` package *after* running `setup_mac.sh` and while the virtual environment (`.venv`) is active.
|
||||
* **Example for `onnxruntime-silicon` (often requires Python 3.10 for older versions like 1.13.1):**
|
||||
The original `README` noted that `onnxruntime-silicon==1.13.1` was specific to Python 3.10. If you intend to use this exact version for CoreML:
|
||||
```bash
|
||||
# Ensure you are using Python 3.10 if required by your chosen onnxruntime-silicon version
|
||||
# After running setup_mac.sh and activating .venv:
|
||||
# source .venv/bin/activate
|
||||
|
||||
pip uninstall onnxruntime onnxruntime-gpu # Uninstall any existing onnxruntime
|
||||
pip install onnxruntime-silicon==1.13.1 # Or your desired version
|
||||
|
||||
# Then use ./run_mac_coreml.sh
|
||||
```
|
||||
Check the ONNX Runtime documentation for the latest recommended packages for Apple Silicon.
|
||||
* **For MPS with ONNX Runtime:** This may require a specific build or version of `onnxruntime`. Consult the ONNX Runtime documentation. For PyTorch-based operations (like the Face Enhancer or Hair Segmenter if they were PyTorch native and not ONNX), PyTorch should automatically try to use MPS on compatible Apple Silicon hardware if available.
|
||||
* **User Interface (Tkinter):** If you encounter errors related to `_tkinter` not being found when launching the UI, ensure your Python installation supports Tk. For Python installed via Homebrew, this is usually `python-tk` (e.g., `brew install python-tk@3.9` or `brew install python-tk@3.10`, matching your Python version).
|
||||
|
||||
** In case something goes wrong and you need to reinstall the virtual environment **
|
||||
|
||||
|
|
|
|||
|
|
@ -41,3 +41,4 @@ show_mouth_mask_box = False
|
|||
mask_feather_ratio = 8
|
||||
mask_down_size = 0.50
|
||||
mask_size = 1
|
||||
enable_hair_swapping = True # Default state for enabling/disabling hair swapping
|
||||
|
|
|
|||
|
|
@ -0,0 +1,110 @@
|
|||
import torch
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
from transformers import SegformerImageProcessor, SegformerForSemanticSegmentation
|
||||
import cv2 # Imported for BGR to RGB conversion, though PIL can also do it.
|
||||
|
||||
# Global variables for caching
|
||||
HAIR_SEGMENTER_PROCESSOR = None
|
||||
HAIR_SEGMENTER_MODEL = None
|
||||
MODEL_NAME = "isjackwild/segformer-b0-finetuned-segments-skin-hair-clothing"
|
||||
|
||||
def segment_hair(image_np: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Segments hair from an image.
|
||||
|
||||
Args:
|
||||
image_np: NumPy array representing the image (BGR format from OpenCV).
|
||||
|
||||
Returns:
|
||||
NumPy array representing the binary hair mask.
|
||||
"""
|
||||
global HAIR_SEGMENTER_PROCESSOR, HAIR_SEGMENTER_MODEL
|
||||
|
||||
if HAIR_SEGMENTER_PROCESSOR is None or HAIR_SEGMENTER_MODEL is None:
|
||||
print(f"Loading hair segmentation model and processor ({MODEL_NAME}) for the first time...")
|
||||
try:
|
||||
HAIR_SEGMENTER_PROCESSOR = SegformerImageProcessor.from_pretrained(MODEL_NAME)
|
||||
HAIR_SEGMENTER_MODEL = SegformerForSemanticSegmentation.from_pretrained(MODEL_NAME)
|
||||
# Optional: Move model to GPU if available and if other models use GPU
|
||||
# if torch.cuda.is_available():
|
||||
# HAIR_SEGMENTER_MODEL = HAIR_SEGMENTER_MODEL.to('cuda')
|
||||
# print("Hair segmentation model moved to GPU.")
|
||||
print("Hair segmentation model and processor loaded successfully.")
|
||||
except Exception as e:
|
||||
print(f"Failed to load hair segmentation model/processor: {e}")
|
||||
# Return an empty mask compatible with expected output shape (H, W)
|
||||
return np.zeros((image_np.shape[0], image_np.shape[1]), dtype=np.uint8)
|
||||
|
||||
# Ensure processor and model are loaded before proceeding
|
||||
if HAIR_SEGMENTER_PROCESSOR is None or HAIR_SEGMENTER_MODEL is None:
|
||||
print("Error: Hair segmentation models are not available.")
|
||||
return np.zeros((image_np.shape[0], image_np.shape[1]), dtype=np.uint8)
|
||||
|
||||
# Convert BGR (OpenCV) to RGB (PIL)
|
||||
image_rgb = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
|
||||
image_pil = Image.fromarray(image_rgb)
|
||||
|
||||
inputs = HAIR_SEGMENTER_PROCESSOR(images=image_pil, return_tensors="pt")
|
||||
|
||||
# Optional: Move inputs to GPU if model is on GPU
|
||||
# if HAIR_SEGMENTER_MODEL.device.type == 'cuda':
|
||||
# inputs = inputs.to(HAIR_SEGMENTER_MODEL.device)
|
||||
|
||||
with torch.no_grad(): # Important for inference
|
||||
outputs = HAIR_SEGMENTER_MODEL(**inputs)
|
||||
|
||||
logits = outputs.logits # Shape: batch_size, num_labels, height, width
|
||||
|
||||
# Upsample logits to original image size
|
||||
upsampled_logits = torch.nn.functional.interpolate(
|
||||
logits,
|
||||
size=(image_np.shape[0], image_np.shape[1]), # H, W
|
||||
mode='bilinear',
|
||||
align_corners=False
|
||||
)
|
||||
|
||||
segmentation_map = upsampled_logits.argmax(dim=1).squeeze().cpu().numpy().astype(np.uint8)
|
||||
|
||||
# Label 2 is for hair in this model
|
||||
return np.where(segmentation_map == 2, 255, 0).astype(np.uint8)
|
||||
|
||||
if __name__ == '__main__':
|
||||
# This is a conceptual test.
|
||||
# In a real scenario, you would load an image using OpenCV or Pillow.
|
||||
# For example:
|
||||
# sample_image_np = cv2.imread("path/to/your/image.jpg")
|
||||
# if sample_image_np is not None:
|
||||
# hair_mask_output = segment_hair(sample_image_np)
|
||||
# cv2.imwrite("hair_mask_output.png", hair_mask_output)
|
||||
# print("Hair mask saved to hair_mask_output.png")
|
||||
# else:
|
||||
# print("Failed to load sample image.")
|
||||
|
||||
print("Conceptual test: Hair segmenter module created.")
|
||||
# Create a dummy image for a basic test run if no image is available.
|
||||
dummy_image_np = np.zeros((100, 100, 3), dtype=np.uint8) # 100x100 BGR image
|
||||
dummy_image_np[:, :, 1] = 255 # Make it green to distinguish from black mask
|
||||
|
||||
try:
|
||||
print("Running segment_hair with a dummy image...")
|
||||
hair_mask_output = segment_hair(dummy_image_np)
|
||||
print(f"segment_hair returned a mask of shape: {hair_mask_output.shape}")
|
||||
# Check if the output is a 2D array (mask) and has the same H, W as input
|
||||
assert hair_mask_output.shape == (dummy_image_np.shape[0], dummy_image_np.shape[1])
|
||||
# Check if the mask is binary (0 or 255)
|
||||
assert np.all(np.isin(hair_mask_output, [0, 255]))
|
||||
print("Dummy image test successful. Hair mask seems to be generated correctly.")
|
||||
|
||||
# Attempt to save the dummy mask (optional, just for visual confirmation if needed)
|
||||
# cv2.imwrite("dummy_hair_mask_output.png", hair_mask_output)
|
||||
# print("Dummy hair mask saved to dummy_hair_mask_output.png")
|
||||
|
||||
except ImportError as e:
|
||||
print(f"An ImportError occurred: {e}. This might be due to missing dependencies like transformers, torch, or Pillow.")
|
||||
print("Please ensure all required packages are installed by updating requirements.txt and installing them.")
|
||||
except Exception as e:
|
||||
print(f"An error occurred during the dummy image test: {e}")
|
||||
print("This could be due to issues with model loading, processing, or other runtime errors.")
|
||||
|
||||
print("To perform a full test, replace the dummy image with a real image path.")
|
||||
|
|
@ -9,6 +9,7 @@ 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.hair_segmenter import segment_hair
|
||||
from modules.utilities import (
|
||||
conditional_download,
|
||||
is_image,
|
||||
|
|
@ -67,15 +68,133 @@ def get_face_swapper() -> Any:
|
|||
return FACE_SWAPPER
|
||||
|
||||
|
||||
def swap_face(source_face: Face, target_face: Face, temp_frame: Frame) -> Frame:
|
||||
def _prepare_warped_source_material_and_mask(
|
||||
source_face_obj: Face,
|
||||
source_frame_full: Frame,
|
||||
matrix: np.ndarray,
|
||||
dsize: tuple
|
||||
) -> tuple[Frame | None, Frame | None]:
|
||||
"""
|
||||
Prepares warped source material (full image) and a combined (face+hair) mask for blending.
|
||||
Returns (None, None) if essential masks cannot be generated.
|
||||
"""
|
||||
# Generate Hair Mask
|
||||
hair_only_mask_source_raw = segment_hair(source_frame_full)
|
||||
if hair_only_mask_source_raw.ndim == 3 and hair_only_mask_source_raw.shape[2] == 3:
|
||||
hair_only_mask_source_raw = cv2.cvtColor(hair_only_mask_source_raw, cv2.COLOR_BGR2GRAY)
|
||||
_, hair_only_mask_source_binary = cv2.threshold(hair_only_mask_source_raw, 127, 255, cv2.THRESH_BINARY)
|
||||
|
||||
# Generate Face Mask
|
||||
face_only_mask_source_raw = create_face_mask(source_face_obj, source_frame_full)
|
||||
_, face_only_mask_source_binary = cv2.threshold(face_only_mask_source_raw, 127, 255, cv2.THRESH_BINARY)
|
||||
|
||||
# Combine Face and Hair Masks
|
||||
if face_only_mask_source_binary.shape != hair_only_mask_source_binary.shape:
|
||||
logging.warning("Resizing hair mask to match face mask for source during preparation.")
|
||||
hair_only_mask_source_binary = cv2.resize(
|
||||
hair_only_mask_source_binary,
|
||||
(face_only_mask_source_binary.shape[1], face_only_mask_source_binary.shape[0]),
|
||||
interpolation=cv2.INTER_NEAREST
|
||||
)
|
||||
|
||||
actual_combined_source_mask = cv2.bitwise_or(face_only_mask_source_binary, hair_only_mask_source_binary)
|
||||
actual_combined_source_mask_blurred = cv2.GaussianBlur(actual_combined_source_mask, (5, 5), 3)
|
||||
|
||||
# Warp the Combined Mask and Full Source Material
|
||||
warped_full_source_material = cv2.warpAffine(source_frame_full, matrix, dsize)
|
||||
warped_combined_mask_temp = cv2.warpAffine(actual_combined_source_mask_blurred, matrix, dsize)
|
||||
_, warped_combined_mask_binary_for_clone = cv2.threshold(warped_combined_mask_temp, 127, 255, cv2.THRESH_BINARY)
|
||||
|
||||
return warped_full_source_material, warped_combined_mask_binary_for_clone
|
||||
|
||||
|
||||
def _blend_material_onto_frame(
|
||||
base_frame: Frame,
|
||||
material_to_blend: Frame,
|
||||
mask_for_blending: Frame
|
||||
) -> Frame:
|
||||
"""
|
||||
Blends material onto a base frame using a mask.
|
||||
Uses seamlessClone if possible, otherwise falls back to simple masking.
|
||||
"""
|
||||
x, y, w, h = cv2.boundingRect(mask_for_blending)
|
||||
output_frame = base_frame # Start with base, will be modified by blending
|
||||
|
||||
if w > 0 and h > 0:
|
||||
center = (x + w // 2, y + h // 2)
|
||||
|
||||
if material_to_blend.shape == base_frame.shape and \
|
||||
material_to_blend.dtype == base_frame.dtype and \
|
||||
mask_for_blending.dtype == np.uint8:
|
||||
try:
|
||||
# Important: seamlessClone modifies the first argument (dst) if it's the same as the output var
|
||||
# So, if base_frame is final_swapped_frame, it will be modified in place.
|
||||
# If we want to keep base_frame pristine, it should be base_frame.copy() if it's also final_swapped_frame.
|
||||
# Given final_swapped_frame is already a copy of swapped_frame at this point, this is fine.
|
||||
output_frame = cv2.seamlessClone(material_to_blend, base_frame, mask_for_blending, center, cv2.NORMAL_CLONE)
|
||||
except cv2.error as e:
|
||||
logging.warning(f"cv2.seamlessClone failed: {e}. Falling back to simple blending.")
|
||||
boolean_mask = mask_for_blending > 127
|
||||
output_frame[boolean_mask] = material_to_blend[boolean_mask]
|
||||
else:
|
||||
logging.warning("Mismatch in shape/type for seamlessClone. Falling back to simple blending.")
|
||||
boolean_mask = mask_for_blending > 127
|
||||
output_frame[boolean_mask] = material_to_blend[boolean_mask]
|
||||
else:
|
||||
logging.info("Warped mask for blending is empty. Skipping blending.")
|
||||
|
||||
return output_frame
|
||||
|
||||
|
||||
def swap_face(source_face_obj: Face, target_face: Face, source_frame_full: Frame, temp_frame: Frame) -> Frame:
|
||||
face_swapper = get_face_swapper()
|
||||
|
||||
# Apply the face swap
|
||||
swapped_frame = face_swapper.get(
|
||||
temp_frame, target_face, source_face, paste_back=True
|
||||
)
|
||||
# Apply the base face swap
|
||||
swapped_frame = face_swapper.get(temp_frame, target_face, source_face_obj, paste_back=True)
|
||||
final_swapped_frame = swapped_frame # Initialize with the base swap. Copy is made only if needed.
|
||||
|
||||
if modules.globals.enable_hair_swapping:
|
||||
if not (source_face_obj.kps is not None and \
|
||||
target_face.kps is not None and \
|
||||
source_face_obj.kps.shape[0] >= 3 and \
|
||||
target_face.kps.shape[0] >= 3):
|
||||
logging.warning(
|
||||
f"Skipping hair blending due to insufficient keypoints. "
|
||||
f"Source kps: {source_face_obj.kps.shape if source_face_obj.kps is not None else 'None'}, "
|
||||
f"Target kps: {target_face.kps.shape if target_face.kps is not None else 'None'}."
|
||||
)
|
||||
else:
|
||||
source_kps_float = source_face_obj.kps.astype(np.float32)
|
||||
target_kps_float = target_face.kps.astype(np.float32)
|
||||
matrix, _ = cv2.estimateAffinePartial2D(source_kps_float, target_kps_float, method=cv2.LMEDS)
|
||||
|
||||
if matrix is None:
|
||||
logging.warning("Failed to estimate affine transformation matrix for hair. Skipping hair blending.")
|
||||
else:
|
||||
dsize = (temp_frame.shape[1], temp_frame.shape[0]) # width, height
|
||||
|
||||
warped_material, warped_mask = _prepare_warped_source_material_and_mask(
|
||||
source_face_obj, source_frame_full, matrix, dsize
|
||||
)
|
||||
|
||||
if warped_material is not None and warped_mask is not None:
|
||||
# Make a copy only now that we are sure we will modify it for hair.
|
||||
final_swapped_frame = swapped_frame.copy()
|
||||
|
||||
color_corrected_material = apply_color_transfer(warped_material, final_swapped_frame) # Use final_swapped_frame for color context
|
||||
|
||||
final_swapped_frame = _blend_material_onto_frame(
|
||||
final_swapped_frame,
|
||||
color_corrected_material,
|
||||
warped_mask
|
||||
)
|
||||
|
||||
# Mouth Mask Logic (operates on final_swapped_frame)
|
||||
if modules.globals.mouth_mask:
|
||||
# If final_swapped_frame wasn't copied for hair, it needs to be copied now before mouth mask modification.
|
||||
if final_swapped_frame is swapped_frame: # Check if it's still the same object
|
||||
final_swapped_frame = swapped_frame.copy()
|
||||
|
||||
# Create a mask for the target face
|
||||
face_mask = create_face_mask(target_face, temp_frame)
|
||||
|
||||
|
|
@ -85,20 +204,21 @@ def swap_face(source_face: Face, target_face: Face, temp_frame: Frame) -> Frame:
|
|||
)
|
||||
|
||||
# Apply the mouth area
|
||||
swapped_frame = apply_mouth_area(
|
||||
swapped_frame, mouth_cutout, mouth_box, face_mask, lower_lip_polygon
|
||||
# Apply to final_swapped_frame if hair blending happened, otherwise to swapped_frame
|
||||
final_swapped_frame = apply_mouth_area(
|
||||
final_swapped_frame, mouth_cutout, mouth_box, face_mask, lower_lip_polygon
|
||||
)
|
||||
|
||||
if modules.globals.show_mouth_mask_box:
|
||||
mouth_mask_data = (mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon)
|
||||
swapped_frame = draw_mouth_mask_visualization(
|
||||
swapped_frame, target_face, mouth_mask_data
|
||||
final_swapped_frame = draw_mouth_mask_visualization(
|
||||
final_swapped_frame, target_face, mouth_mask_data
|
||||
)
|
||||
|
||||
return swapped_frame
|
||||
return final_swapped_frame
|
||||
|
||||
|
||||
def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
|
||||
def process_frame(source_face_obj: Face, source_frame_full: Frame, temp_frame: Frame) -> Frame:
|
||||
if modules.globals.color_correction:
|
||||
temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
|
||||
|
||||
|
|
@ -106,152 +226,192 @@ def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
|
|||
many_faces = get_many_faces(temp_frame)
|
||||
if many_faces:
|
||||
for target_face in many_faces:
|
||||
if source_face and target_face:
|
||||
temp_frame = swap_face(source_face, target_face, temp_frame)
|
||||
if source_face_obj and target_face:
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
else:
|
||||
print("Face detection failed for target/source.")
|
||||
else:
|
||||
target_face = get_one_face(temp_frame)
|
||||
if target_face and source_face:
|
||||
temp_frame = swap_face(source_face, target_face, temp_frame)
|
||||
if target_face and source_face_obj:
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
else:
|
||||
logging.error("Face detection failed for target or source.")
|
||||
return temp_frame
|
||||
|
||||
|
||||
# process_frame_v2 needs to accept source_frame_full as well
|
||||
|
||||
def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
|
||||
if is_image(modules.globals.target_path):
|
||||
if modules.globals.many_faces:
|
||||
source_face = default_source_face()
|
||||
for map in modules.globals.source_target_map:
|
||||
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.source_target_map:
|
||||
if "source" in map:
|
||||
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.source_target_map:
|
||||
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"]:
|
||||
temp_frame = swap_face(source_face, target_face, temp_frame)
|
||||
|
||||
elif not modules.globals.many_faces:
|
||||
for map in modules.globals.source_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"]
|
||||
|
||||
for frame in target_frame:
|
||||
for target_face in frame["faces"]:
|
||||
temp_frame = swap_face(source_face, target_face, temp_frame)
|
||||
|
||||
else:
|
||||
detected_faces = get_many_faces(temp_frame)
|
||||
if modules.globals.many_faces:
|
||||
if detected_faces:
|
||||
source_face = default_source_face()
|
||||
for target_face in detected_faces:
|
||||
temp_frame = swap_face(source_face, target_face, temp_frame)
|
||||
|
||||
elif not modules.globals.many_faces:
|
||||
if detected_faces:
|
||||
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,
|
||||
)
|
||||
|
||||
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)
|
||||
i = 0
|
||||
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,
|
||||
)
|
||||
i += 1
|
||||
def _process_image_target_v2(source_frame_full: Frame, temp_frame: Frame) -> Frame:
|
||||
if modules.globals.many_faces:
|
||||
source_face_obj = default_source_face()
|
||||
if source_face_obj:
|
||||
for map_item in modules.globals.source_target_map:
|
||||
target_face = map_item["target"]["face"]
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
else: # not many_faces
|
||||
for map_item in modules.globals.source_target_map:
|
||||
if "source" in map_item:
|
||||
source_face_obj = map_item["source"]["face"]
|
||||
target_face = map_item["target"]["face"]
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
return temp_frame
|
||||
|
||||
def _process_video_target_v2(source_frame_full: Frame, temp_frame: Frame, temp_frame_path: str) -> Frame:
|
||||
if modules.globals.many_faces:
|
||||
source_face_obj = default_source_face()
|
||||
if source_face_obj:
|
||||
for map_item in modules.globals.source_target_map:
|
||||
target_frames_data = [f for f in map_item.get("target_faces_in_frame", []) if f.get("location") == temp_frame_path]
|
||||
for frame_data in target_frames_data:
|
||||
for target_face in frame_data.get("faces", []):
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
else: # not many_faces
|
||||
for map_item in modules.globals.source_target_map:
|
||||
if "source" in map_item:
|
||||
source_face_obj = map_item["source"]["face"]
|
||||
target_frames_data = [f for f in map_item.get("target_faces_in_frame", []) if f.get("location") == temp_frame_path]
|
||||
for frame_data in target_frames_data:
|
||||
for target_face in frame_data.get("faces", []):
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
return temp_frame
|
||||
|
||||
def _process_live_target_v2(source_frame_full: Frame, temp_frame: Frame) -> Frame:
|
||||
detected_faces = get_many_faces(temp_frame)
|
||||
if not detected_faces:
|
||||
return temp_frame
|
||||
|
||||
if modules.globals.many_faces:
|
||||
source_face_obj = default_source_face()
|
||||
if source_face_obj:
|
||||
for target_face in detected_faces:
|
||||
temp_frame = swap_face(source_face_obj, target_face, source_frame_full, temp_frame)
|
||||
else: # not many_faces (apply simple_map logic)
|
||||
if not modules.globals.simple_map or \
|
||||
not modules.globals.simple_map.get("target_embeddings") or \
|
||||
not modules.globals.simple_map.get("source_faces"):
|
||||
logging.warning("Simple map is not configured correctly. Skipping face swap.")
|
||||
return temp_frame
|
||||
|
||||
target_embeddings = modules.globals.simple_map["target_embeddings"]
|
||||
source_faces_from_map = modules.globals.simple_map["source_faces"]
|
||||
|
||||
if len(detected_faces) <= len(target_embeddings):
|
||||
for detected_face in detected_faces:
|
||||
closest_centroid_index, _ = find_closest_centroid(target_embeddings, detected_face.normed_embedding)
|
||||
if closest_centroid_index < len(source_faces_from_map):
|
||||
source_face_obj_from_map = source_faces_from_map[closest_centroid_index]
|
||||
temp_frame = swap_face(source_face_obj_from_map, detected_face, source_frame_full, temp_frame)
|
||||
else:
|
||||
logging.warning(f"Centroid index {closest_centroid_index} out of bounds for source_faces_from_map.")
|
||||
else: # More detected faces than target embeddings in simple_map
|
||||
detected_faces_embeddings = [face.normed_embedding for face in detected_faces]
|
||||
for i, target_embedding in enumerate(target_embeddings):
|
||||
if i < len(source_faces_from_map):
|
||||
closest_detected_face_index, _ = find_closest_centroid(detected_faces_embeddings, target_embedding)
|
||||
source_face_obj_from_map = source_faces_from_map[i]
|
||||
target_face_to_swap = detected_faces[closest_detected_face_index]
|
||||
temp_frame = swap_face(source_face_obj_from_map, target_face_to_swap, source_frame_full, temp_frame)
|
||||
# Optionally, remove the swapped detected face to prevent re-swapping if one source maps to multiple targets.
|
||||
# This depends on desired behavior. For now, simple independent mapping.
|
||||
else:
|
||||
logging.warning(f"Index {i} out of bounds for source_faces_from_map in simple_map else case.")
|
||||
return temp_frame
|
||||
|
||||
|
||||
def process_frame_v2(source_frame_full: Frame, temp_frame: Frame, temp_frame_path: str = "") -> Frame:
|
||||
if is_image(modules.globals.target_path):
|
||||
return _process_image_target_v2(source_frame_full, temp_frame)
|
||||
elif is_video(modules.globals.target_path):
|
||||
return _process_video_target_v2(source_frame_full, temp_frame, temp_frame_path)
|
||||
else: # This is the live cam / generic case
|
||||
return _process_live_target_v2(source_frame_full, temp_frame)
|
||||
|
||||
|
||||
def process_frames(
|
||||
source_path: str, temp_frame_paths: List[str], progress: Any = None
|
||||
) -> None:
|
||||
source_img = cv2.imread(source_path)
|
||||
if source_img is None:
|
||||
logging.error(f"Failed to read source image from {source_path}")
|
||||
return
|
||||
|
||||
if not modules.globals.map_faces:
|
||||
source_face = get_one_face(cv2.imread(source_path))
|
||||
source_face_obj = get_one_face(source_img) # Use source_img here
|
||||
if not source_face_obj:
|
||||
logging.error(f"No face detected in source image {source_path}")
|
||||
return
|
||||
for temp_frame_path in temp_frame_paths:
|
||||
temp_frame = cv2.imread(temp_frame_path)
|
||||
if temp_frame is None:
|
||||
logging.warning(f"Failed to read temp_frame from {temp_frame_path}, skipping.")
|
||||
continue
|
||||
try:
|
||||
result = process_frame(source_face, temp_frame)
|
||||
result = process_frame(source_face_obj, source_img, temp_frame)
|
||||
cv2.imwrite(temp_frame_path, result)
|
||||
except Exception as exception:
|
||||
print(exception)
|
||||
logging.error(f"Error processing frame {temp_frame_path}: {exception}", exc_info=True)
|
||||
pass
|
||||
if progress:
|
||||
progress.update(1)
|
||||
else:
|
||||
else: # This is for map_faces == True
|
||||
# In map_faces=True, source_face is determined per mapping.
|
||||
# process_frame_v2 will need source_frame_full for hair,
|
||||
# which should be the original source_path image.
|
||||
for temp_frame_path in temp_frame_paths:
|
||||
temp_frame = cv2.imread(temp_frame_path)
|
||||
if temp_frame is None:
|
||||
logging.warning(f"Failed to read temp_frame from {temp_frame_path}, skipping.")
|
||||
continue
|
||||
try:
|
||||
result = process_frame_v2(temp_frame, temp_frame_path)
|
||||
# Pass source_img (as source_frame_full) to process_frame_v2
|
||||
result = process_frame_v2(source_img, temp_frame, temp_frame_path)
|
||||
cv2.imwrite(temp_frame_path, result)
|
||||
except Exception as exception:
|
||||
print(exception)
|
||||
logging.error(f"Error processing frame {temp_frame_path} with map_faces: {exception}", exc_info=True)
|
||||
pass
|
||||
if progress:
|
||||
progress.update(1)
|
||||
|
||||
|
||||
def process_image(source_path: str, target_path: str, output_path: str) -> None:
|
||||
source_img = cv2.imread(source_path)
|
||||
if source_img is None:
|
||||
logging.error(f"Failed to read source image from {source_path}")
|
||||
return
|
||||
|
||||
target_frame = cv2.imread(target_path)
|
||||
if target_frame is None:
|
||||
logging.error(f"Failed to read target image from {target_path}")
|
||||
return
|
||||
|
||||
# Read the original target frame once at the beginning
|
||||
original_target_frame = cv2.imread(target_path)
|
||||
if original_target_frame is None:
|
||||
logging.error(f"Failed to read original target image from {target_path}")
|
||||
return
|
||||
|
||||
result = None # Initialize result
|
||||
|
||||
if not modules.globals.map_faces:
|
||||
source_face = get_one_face(cv2.imread(source_path))
|
||||
target_frame = cv2.imread(target_path)
|
||||
result = process_frame(source_face, target_frame)
|
||||
cv2.imwrite(output_path, result)
|
||||
else:
|
||||
source_face_obj = get_one_face(source_img) # Use source_img here
|
||||
if not source_face_obj:
|
||||
logging.error(f"No face detected in source image {source_path}")
|
||||
return
|
||||
result = process_frame(source_face_obj, source_img, original_target_frame)
|
||||
else: # map_faces is True
|
||||
if modules.globals.many_faces:
|
||||
update_status(
|
||||
"Many faces enabled. Using first source image. Progressing...", NAME
|
||||
)
|
||||
target_frame = cv2.imread(output_path)
|
||||
result = process_frame_v2(target_frame)
|
||||
# process_frame_v2 takes the original target frame for processing.
|
||||
# target_path is passed as temp_frame_path for consistency with process_frame_v2's signature,
|
||||
# used for map lookups in video context but less critical for single images.
|
||||
result = process_frame_v2(source_img, original_target_frame, target_path)
|
||||
|
||||
if result is not None:
|
||||
cv2.imwrite(output_path, result)
|
||||
else:
|
||||
logging.error(f"Processing image {target_path} failed, result was None.")
|
||||
|
||||
|
||||
def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
|
||||
|
|
|
|||
163
modules/ui.py
163
modules/ui.py
|
|
@ -105,6 +105,7 @@ def save_switch_states():
|
|||
"show_fps": modules.globals.show_fps,
|
||||
"mouth_mask": modules.globals.mouth_mask,
|
||||
"show_mouth_mask_box": modules.globals.show_mouth_mask_box,
|
||||
"enable_hair_swapping": modules.globals.enable_hair_swapping,
|
||||
}
|
||||
with open("switch_states.json", "w") as f:
|
||||
json.dump(switch_states, f)
|
||||
|
|
@ -129,6 +130,9 @@ def load_switch_states():
|
|||
modules.globals.show_mouth_mask_box = switch_states.get(
|
||||
"show_mouth_mask_box", False
|
||||
)
|
||||
modules.globals.enable_hair_swapping = switch_states.get(
|
||||
"enable_hair_swapping", True # Default to True if not found
|
||||
)
|
||||
except FileNotFoundError:
|
||||
# If the file doesn't exist, use default values
|
||||
pass
|
||||
|
|
@ -284,6 +288,20 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
|
|||
)
|
||||
show_fps_switch.place(relx=0.6, rely=0.75)
|
||||
|
||||
# Hair Swapping Switch (placed below "Show FPS" on the right column)
|
||||
hair_swapping_value = ctk.BooleanVar(value=modules.globals.enable_hair_swapping)
|
||||
hair_swapping_switch = ctk.CTkSwitch(
|
||||
root,
|
||||
text=_("Swap Hair"),
|
||||
variable=hair_swapping_value,
|
||||
cursor="hand2",
|
||||
command=lambda: (
|
||||
setattr(modules.globals, "enable_hair_swapping", hair_swapping_value.get()),
|
||||
save_switch_states(),
|
||||
)
|
||||
)
|
||||
hair_swapping_switch.place(relx=0.6, rely=0.80) # Adjusted rely from 0.75 to 0.80
|
||||
|
||||
mouth_mask_var = ctk.BooleanVar(value=modules.globals.mouth_mask)
|
||||
mouth_mask_switch = ctk.CTkSwitch(
|
||||
root,
|
||||
|
|
@ -306,24 +324,26 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
|
|||
)
|
||||
show_mouth_mask_box_switch.place(relx=0.6, rely=0.55)
|
||||
|
||||
# Adjusting placement of Start, Stop, Preview buttons due to new switch
|
||||
start_button = ctk.CTkButton(
|
||||
root, text=_("Start"), cursor="hand2", command=lambda: analyze_target(start, root)
|
||||
)
|
||||
start_button.place(relx=0.15, rely=0.80, relwidth=0.2, relheight=0.05)
|
||||
start_button.place(relx=0.15, rely=0.85, relwidth=0.2, relheight=0.05) # rely from 0.80 to 0.85
|
||||
|
||||
stop_button = ctk.CTkButton(
|
||||
root, text=_("Destroy"), cursor="hand2", command=lambda: destroy()
|
||||
)
|
||||
stop_button.place(relx=0.4, rely=0.80, relwidth=0.2, relheight=0.05)
|
||||
stop_button.place(relx=0.4, rely=0.85, relwidth=0.2, relheight=0.05) # rely from 0.80 to 0.85
|
||||
|
||||
preview_button = ctk.CTkButton(
|
||||
root, text=_("Preview"), cursor="hand2", command=lambda: toggle_preview()
|
||||
)
|
||||
preview_button.place(relx=0.65, rely=0.80, relwidth=0.2, relheight=0.05)
|
||||
preview_button.place(relx=0.65, rely=0.85, relwidth=0.2, relheight=0.05) # rely from 0.80 to 0.85
|
||||
|
||||
# --- Camera Selection ---
|
||||
# Adjusting placement of Camera selection due to new switch
|
||||
camera_label = ctk.CTkLabel(root, text=_("Select Camera:"))
|
||||
camera_label.place(relx=0.1, rely=0.86, relwidth=0.2, relheight=0.05)
|
||||
camera_label.place(relx=0.1, rely=0.91, relwidth=0.2, relheight=0.05) # rely from 0.86 to 0.91
|
||||
|
||||
available_cameras = get_available_cameras()
|
||||
camera_indices, camera_names = available_cameras
|
||||
|
|
@ -342,7 +362,7 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
|
|||
root, variable=camera_variable, values=camera_names
|
||||
)
|
||||
|
||||
camera_optionmenu.place(relx=0.35, rely=0.86, relwidth=0.25, relheight=0.05)
|
||||
camera_optionmenu.place(relx=0.35, rely=0.91, relwidth=0.25, relheight=0.05) # rely from 0.86 to 0.91
|
||||
|
||||
live_button = ctk.CTkButton(
|
||||
root,
|
||||
|
|
@ -362,16 +382,16 @@ def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.C
|
|||
else "disabled"
|
||||
),
|
||||
)
|
||||
live_button.place(relx=0.65, rely=0.86, relwidth=0.2, relheight=0.05)
|
||||
live_button.place(relx=0.65, rely=0.91, relwidth=0.2, relheight=0.05) # rely from 0.86 to 0.91
|
||||
# --- End Camera Selection ---
|
||||
|
||||
status_label = ctk.CTkLabel(root, text=None, justify="center")
|
||||
status_label.place(relx=0.1, rely=0.9, relwidth=0.8)
|
||||
status_label.place(relx=0.1, rely=0.96, relwidth=0.8) # rely from 0.9 to 0.96
|
||||
|
||||
donate_label = ctk.CTkLabel(
|
||||
root, text="Deep Live Cam", justify="center", cursor="hand2"
|
||||
)
|
||||
donate_label.place(relx=0.1, rely=0.95, relwidth=0.8)
|
||||
donate_label.place(relx=0.1, rely=0.99, relwidth=0.8) # rely from 0.95 to 0.99
|
||||
donate_label.configure(
|
||||
text_color=ctk.ThemeManager.theme.get("URL").get("text_color")
|
||||
)
|
||||
|
|
@ -880,7 +900,94 @@ def create_webcam_preview(camera_index: int):
|
|||
PREVIEW.deiconify()
|
||||
|
||||
frame_processors = get_frame_processors_modules(modules.globals.frame_processors)
|
||||
source_image = None
|
||||
|
||||
# --- Source Image Loading and Validation (Moved before the loop) ---
|
||||
source_face_obj_for_cam = None
|
||||
source_frame_full_for_cam = None
|
||||
source_frame_full_for_cam_map_faces = None
|
||||
|
||||
if not modules.globals.map_faces:
|
||||
if not modules.globals.source_path:
|
||||
update_status("Error: No source image selected for webcam mode.")
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
if not os.path.exists(modules.globals.source_path):
|
||||
update_status(f"Error: Source image not found at {modules.globals.source_path}")
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
|
||||
source_frame_full_for_cam = cv2.imread(modules.globals.source_path)
|
||||
if source_frame_full_for_cam is None:
|
||||
update_status(f"Error: Could not read source image at {modules.globals.source_path}")
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
|
||||
source_face_obj_for_cam = get_one_face(source_frame_full_for_cam)
|
||||
if source_face_obj_for_cam is None:
|
||||
update_status(f"Error: No face detected in source image {modules.globals.source_path}")
|
||||
# This error is less critical for stopping immediately, but we'll make it persistent too.
|
||||
# The loop below will run, but processing for frames will effectively be skipped.
|
||||
# For consistency in error handling, make it persistent.
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
else: # modules.globals.map_faces is True
|
||||
if not modules.globals.source_path:
|
||||
update_status("Error: No global source image selected (for hair/background in map_faces mode).")
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
if not os.path.exists(modules.globals.source_path):
|
||||
update_status(f"Error: Source image (for hair/background) not found at {modules.globals.source_path}")
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
|
||||
source_frame_full_for_cam_map_faces = cv2.imread(modules.globals.source_path)
|
||||
if source_frame_full_for_cam_map_faces is None:
|
||||
update_status(f"Error: Could not read source image (for hair/background) at {modules.globals.source_path}")
|
||||
cap.release()
|
||||
PREVIEW.withdraw()
|
||||
while PREVIEW.state() != "withdrawn" and ROOT.winfo_exists():
|
||||
ROOT.update_idletasks()
|
||||
ROOT.update()
|
||||
time.sleep(0.05)
|
||||
return
|
||||
|
||||
if not modules.globals.source_target_map and not modules.globals.simple_map:
|
||||
update_status("Warning: No face map defined for map_faces mode. Swapper may not work as expected.")
|
||||
# This is a warning, not a fatal error for the preview window itself. Processing will continue.
|
||||
# No persistent loop here, as it's a warning about functionality, not a critical load error.
|
||||
|
||||
# --- End Source Image Loading ---
|
||||
|
||||
prev_time = time.time()
|
||||
fps_update_interval = 0.5
|
||||
frame_count = 0
|
||||
|
|
@ -907,23 +1014,29 @@ def create_webcam_preview(camera_index: int):
|
|||
)
|
||||
|
||||
if not modules.globals.map_faces:
|
||||
if source_image is None and modules.globals.source_path:
|
||||
source_image = get_one_face(cv2.imread(modules.globals.source_path))
|
||||
|
||||
for frame_processor in frame_processors:
|
||||
if frame_processor.NAME == "DLC.FACE-ENHANCER":
|
||||
if modules.globals.fp_ui["face_enhancer"]:
|
||||
temp_frame = frame_processor.process_frame(None, temp_frame)
|
||||
else:
|
||||
temp_frame = frame_processor.process_frame(source_image, temp_frame)
|
||||
if not modules.globals.map_faces:
|
||||
# Case 1: map_faces is False - source_face_obj_for_cam and source_frame_full_for_cam are pre-loaded
|
||||
if source_face_obj_for_cam and source_frame_full_for_cam is not None: # Check if valid after pre-loading
|
||||
for frame_processor in frame_processors:
|
||||
if frame_processor.NAME == "DLC.FACE-ENHANCER":
|
||||
if modules.globals.fp_ui["face_enhancer"]:
|
||||
temp_frame = frame_processor.process_frame(None, temp_frame)
|
||||
else:
|
||||
temp_frame = frame_processor.process_frame(source_face_obj_for_cam, source_frame_full_for_cam, temp_frame)
|
||||
# If source image was invalid (e.g. no face), source_face_obj_for_cam might be None.
|
||||
# In this case, the frame processors that need it will be skipped, effectively just showing the raw webcam frame.
|
||||
# The error message is already persistent due to the pre-loop check.
|
||||
else:
|
||||
modules.globals.target_path = None
|
||||
for frame_processor in frame_processors:
|
||||
if frame_processor.NAME == "DLC.FACE-ENHANCER":
|
||||
if modules.globals.fp_ui["face_enhancer"]:
|
||||
temp_frame = frame_processor.process_frame_v2(temp_frame)
|
||||
else:
|
||||
temp_frame = frame_processor.process_frame_v2(temp_frame)
|
||||
# Case 2: map_faces is True - source_frame_full_for_cam_map_faces is pre-loaded
|
||||
if source_frame_full_for_cam_map_faces is not None: # Check if valid after pre-loading
|
||||
modules.globals.target_path = None # Standard for live mode
|
||||
for frame_processor in frame_processors:
|
||||
if frame_processor.NAME == "DLC.FACE-ENHANCER":
|
||||
if modules.globals.fp_ui["face_enhancer"]:
|
||||
temp_frame = frame_processor.process_frame_v2(source_frame_full_for_cam_map_faces, temp_frame)
|
||||
else:
|
||||
temp_frame = frame_processor.process_frame_v2(source_frame_full_for_cam_map_faces, temp_frame)
|
||||
# If source_frame_full_for_cam_map_faces was invalid, error is persistent from pre-loop check.
|
||||
|
||||
# Calculate and display FPS
|
||||
current_time = time.time()
|
||||
|
|
|
|||
|
|
@ -19,3 +19,4 @@ onnxruntime-gpu==1.17; sys_platform != 'darwin'
|
|||
tensorflow; sys_platform != 'darwin'
|
||||
opennsfw2==0.10.2
|
||||
protobuf==4.23.2
|
||||
transformers>=4.0.0
|
||||
|
|
|
|||
|
|
@ -0,0 +1,20 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
VENV_DIR=".venv"
|
||||
|
||||
# Check if virtual environment exists
|
||||
if [ ! -d "$VENV_DIR" ]; then
|
||||
echo "Virtual environment '$VENV_DIR' not found."
|
||||
echo "Please run ./setup_mac.sh first to create the environment and install dependencies."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Activating virtual environment..."
|
||||
source "$VENV_DIR/bin/activate"
|
||||
|
||||
echo "Starting the application with CPU execution provider..."
|
||||
# Passes all arguments passed to this script (e.g., --source, --target) to run.py
|
||||
python3 run.py --execution-provider cpu "$@"
|
||||
|
||||
# Deactivate after script finishes (optional, as shell context closes)
|
||||
# deactivate
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
VENV_DIR=".venv"
|
||||
|
||||
if [ ! -d "$VENV_DIR" ]; then
|
||||
echo "Virtual environment '$VENV_DIR' not found."
|
||||
echo "Please run ./setup_mac.sh first."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
source "$VENV_DIR/bin/activate"
|
||||
echo "Starting the application with CoreML execution provider..."
|
||||
python3 run.py --execution-provider coreml "$@"
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
VENV_DIR=".venv"
|
||||
|
||||
if [ ! -d "$VENV_DIR" ]; then
|
||||
echo "Virtual environment '$VENV_DIR' not found."
|
||||
echo "Please run ./setup_mac.sh first."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
source "$VENV_DIR/bin/activate"
|
||||
echo "Starting the application with CPU execution provider..."
|
||||
python3 run.py --execution-provider cpu "$@"
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
VENV_DIR=".venv"
|
||||
|
||||
if [ ! -d "$VENV_DIR" ]; then
|
||||
echo "Virtual environment '$VENV_DIR' not found."
|
||||
echo "Please run ./setup_mac.sh first."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
source "$VENV_DIR/bin/activate"
|
||||
echo "Starting the application with MPS execution provider (for Apple Silicon)..."
|
||||
python3 run.py --execution-provider mps "$@"
|
||||
|
|
@ -0,0 +1,81 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
# Exit immediately if a command exits with a non-zero status.
|
||||
set -e
|
||||
|
||||
echo "Starting macOS setup..."
|
||||
|
||||
# 1. Check for Python 3
|
||||
echo "Checking for Python 3..."
|
||||
if ! command -v python3 &> /dev/null
|
||||
then
|
||||
echo "Python 3 could not be found. Please install Python 3."
|
||||
echo "You can often install it using Homebrew: brew install python"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 2. Check Python version (>= 3.9)
|
||||
echo "Checking Python 3 version..."
|
||||
python3 -c 'import sys; exit(0) if sys.version_info >= (3,9) else exit(1)'
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Python 3.9 or higher is required."
|
||||
echo "Your version is: $(python3 --version)"
|
||||
echo "Please upgrade your Python version. Consider using pyenv or Homebrew to manage Python versions."
|
||||
exit 1
|
||||
fi
|
||||
echo "Python 3.9+ found: $(python3 --version)"
|
||||
|
||||
# 3. Check for ffmpeg
|
||||
echo "Checking for ffmpeg..."
|
||||
if ! command -v ffmpeg &> /dev/null
|
||||
then
|
||||
echo "WARNING: ffmpeg could not be found. This program requires ffmpeg for video processing."
|
||||
echo "You can install it using Homebrew: brew install ffmpeg"
|
||||
echo "Continuing with setup, but video processing might fail later."
|
||||
else
|
||||
echo "ffmpeg found: $(ffmpeg -version | head -n 1)"
|
||||
fi
|
||||
|
||||
# 4. Define virtual environment directory
|
||||
VENV_DIR=".venv"
|
||||
|
||||
# 5. Create virtual environment
|
||||
if [ -d "$VENV_DIR" ]; then
|
||||
echo "Virtual environment '$VENV_DIR' already exists. Skipping creation."
|
||||
else
|
||||
echo "Creating virtual environment in '$VENV_DIR'..."
|
||||
python3 -m venv "$VENV_DIR"
|
||||
fi
|
||||
|
||||
# 6. Activate virtual environment (for this script's session)
|
||||
echo "Activating virtual environment..."
|
||||
source "$VENV_DIR/bin/activate"
|
||||
|
||||
# 7. Upgrade pip
|
||||
echo "Upgrading pip..."
|
||||
pip install --upgrade pip
|
||||
|
||||
# 8. Install requirements
|
||||
echo "Installing requirements from requirements.txt..."
|
||||
if [ -f "requirements.txt" ]; then
|
||||
pip install -r requirements.txt
|
||||
else
|
||||
echo "ERROR: requirements.txt not found. Cannot install dependencies."
|
||||
# Deactivate on error if desired, or leave active for user to debug
|
||||
# deactivate
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "Setup complete!"
|
||||
echo ""
|
||||
echo "To activate the virtual environment in your terminal, run:"
|
||||
echo " source $VENV_DIR/bin/activate"
|
||||
echo ""
|
||||
echo "After activating, you can run the application using:"
|
||||
echo " python3 run.py [arguments]"
|
||||
echo "Or use one of the run_mac_*.sh scripts (e.g., ./run_mac_cpu.sh)."
|
||||
echo ""
|
||||
|
||||
# Deactivate at the end of the script's execution (optional, as script session ends)
|
||||
# deactivate
|
||||
Loading…
Reference in New Issue