ComfyUI Node
cv2.ximgproc.fastBilateralSolverFilter
REQUIRES AN OPENCV BUILT WITH THE EIGEN LIBRARY - NOT AVAILABLE IN THIS BUILD ('Eigen: NO'), SO EVERY CALL RAISES OpenCV ERROR (-213). Install an Eigen-enabled OpenCV build to use it. Raw wrapper of cv2.ximgproc.fastBilateralSolverFilter(guide, src, confidence, sigma_spatial?, sigma_luma?, sigma_chroma?, lambda_?, num_iter?, max_tol?). Parameters marked '?' are optional; blank means OpenCV default. From the opencv-contrib 'ximgproc' module. See the OpenCV documentation for details.
cv2.ximgproc.fastBilateralSolverFilter
- guide
- src
- confidence
- nparray
◄sigma_spatial8.0000►
◄sigma_luma8.0000►
◄sigma_chroma8.0000►
◄lambda_128.0000►
◄num_iter25►
◄max_tol0.0000►
Categoryimage/CV/low-level/ximgproc
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| guide | NPARRAY,IMAGE,MASK | image serving as guide for filtering. It should have 8-bit depth and either 1 or 3 channels. Accepts a ComfyUI IMAGE/MASK directly (frame 0 of a batch) or an NPARRAY. Arithmetic ops (add, multiply, etc.) process the full IMAGE batch when both inputs have the same batch size. | |
| src | NPARRAY,IMAGE,MASK | source image for filtering with unsigned 8-bit or signed 16-bit or floating-point 32-bit depth and up to 4 channels. Accepts a ComfyUI IMAGE/MASK directly (frame 0 of a batch) or an NPARRAY. Arithmetic ops (add, multiply, etc.) process the full IMAGE batch when both inputs have the same batch size. | |
| confidence | NPARRAY,IMAGE,MASK | confidence image with unsigned 8-bit or floating-point 32-bit confidence and 1 channel. Accepts a ComfyUI IMAGE/MASK directly (frame 0 of a batch) or an NPARRAY. Arithmetic ops (add, multiply, etc.) process the full IMAGE batch when both inputs have the same batch size. | |
| sigma_spatialopt | FLOAT | 8.0000-1e+38–1e+38 | parameter, that is similar to spatial space sigma (bandwidth) in bilateralFilter. Preset to the OpenCV default (8.0). |
| sigma_lumaopt | FLOAT | 8.0000-1e+38–1e+38 | parameter, that is similar to luma space sigma (bandwidth) in bilateralFilter. Preset to the OpenCV default (8.0). |
| sigma_chromaopt | FLOAT | 8.0000-1e+38–1e+38 | parameter, that is similar to chroma space sigma (bandwidth) in bilateralFilter. Preset to the OpenCV default (8.0). |
| lambda_opt | FLOAT | 128.0000-1e+38–1e+38 | - - - Preset to the OpenCV default (128.0). |
| num_iteropt | INT | 25-2147483648–2147483647 | number of iterations used for solver, 25 is usually enough. Preset to the OpenCV default (25). |
| max_tolopt | FLOAT | 0.0000-1e+38–1e+38 | convergence tolerance used for solver. For more details about the Fast Bilateral Solver parameters, see the original paper . Preset to the OpenCV default (1e-05). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| nparray | NPARRAY | — |