Spaces:
Running
Running
AIO Aux Preprocessor
intergrating all loadable aux preprocessors as dropdown options. Easy to copy, paste and get the preprocessor faster.- Added OpenPose-format JSON output from OpenPose Preprocessor and DWPose Preprocessor. Checks here.
- Fixed wrong model path when downloading DWPose.
- Make hint images less blurry.
- Added
resolution
option,PixelPerfectResolution
andHintImageEnchance
nodes (TODO: Documentation). - Added
RAFT Optical Flow Embedder
for TemporalNet2 (TODO: Workflow example). - Fixed opencv's conflicts between this extension, ReActor and Roop. Thanks
Gourieff
for the solution! - RAFT is removed as the code behind it doesn't match what what the original code does
- Changed
lineart
's display name fromNormal Lineart
toRealistic Lineart
. This change won't affect old workflows - Added support for
onnxruntime
to speed-up DWPose (see the Q&A) - Fixed TypeError: expected size to be one of int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int], but got size with types [<class 'numpy.int64'>, <class 'numpy.int64'>]: Issue, PR)
- Fixed ImageGenResolutionFromImage mishape (https://github.com/Fannovel16/comfyui_controlnet_aux/pull/74)
- Fixed LeRes and MiDaS's incomatipility with MPS device
- Fixed checking DWPose onnxruntime session multiple times: https://github.com/Fannovel16/comfyui_controlnet_aux/issues/89)
- Added
Anime Face Segmentor
(inControlNet Preprocessors/Semantic Segmentation
) for ControlNet AnimeFaceSegmentV2. Checks here - Change download functions and fix download error: PR
- Caching DWPose Onnxruntime during the first use of DWPose node instead of ComfyUI startup
- Added alternative YOLOX models for faster speed when using DWPose
- Added alternative DWPose models
- Implemented the preprocessor for AnimalPose ControlNet. Check Animal Pose AP-10K
- Added YOLO-NAS models which are drop-in replacements of YOLOX
- Fixed Openpose Face/Hands no longer detecting: https://github.com/Fannovel16/comfyui_controlnet_aux/issues/54
- Added TorchScript implementation of DWPose and AnimalPose
- Added TorchScript implementation of DensePose from Colab notebook which doesn't require detectron2. Example. Thanks @LayerNome for fixing bugs related.
- Added Standard Lineart Preprocessor
- Fixed OpenPose misplacements in some cases
- Added Mesh Graphormer - Hand Depth Map & Mask
- Misaligned hands bug from MeshGraphormer was fixed
- Added more mask options for MeshGraphormer
- Added Save Pose Keypoint node for editing
- Added Unimatch Optical Flow
- Added Depth Anything & Zoe Depth Anything
- Removed resolution field from Unimatch Optical Flow as that interpolating optical flow seems unstable
- Added TEED Soft-Edge Preprocessor
- Added DiffusionEdge
- Added Image Luminance and Image Intensity
- Added Normal DSINE
- Added TTPlanet Tile (09/05/2024, DD/MM/YYYY)
- Added AnyLine, Metric3D (18/05/2024)
- Added Depth Anything V2 (16/06/2024)
- Added Union model of ControlNet and preprocessors
- Refactor INPUT_TYPES and add Execute All node during the process of learning Execution Model Inversion
- Added scale_stick_for_xinsr_cn (https://github.com/Fannovel16/comfyui_controlnet_aux/issues/447) (09/04/2024)