ComfyUI Node
Yogurt Sa2VA Image Segmentation V2
Segment one image with a reusable Sa2VA model and optional VITMatte detail refinement.
Yogurt Sa2VA Image Segmentation V2
- sa2va_model
- vitmatte_model
- image
- text_output
- masks
◄segmentation_promptPlease provide segmentation masks for all objects.►
◄threshold0.50►
◄process_detailtrue►
◄detail_erode6►
◄detail_dilate6►
◄black_point0.15►
◄white_point0.99►
◄max_megapixels2.0►
CategoryYogurtSa2VA
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| sa2va_model | YOGURT_SA2VA_MODEL | — | |
| vitmatte_model | YOGURT_VITMATTE_MODEL | — | |
| image | IMAGE | Input image to segment. Should be in RGB format. | |
| segmentation_prompt | STRING | Please provide segmentation masks for all objects. | Text prompt describing what objects to segment in the image. |
| threshold | FLOAT | 0.500–1 | Threshold for converting probability masks to binary masks. |
| process_detail | BOOLEAN | true | Enable VITMatte post-processing for smooth edges and fine details. |
| detail_erode | INT | 61–255 | Erosion kernel size for trimap generation. |
| detail_dilate | INT | 61–255 | Dilation kernel size for trimap generation. |
| black_point | FLOAT | 0.150.01–0.98 | — |
| white_point | FLOAT | 0.990.02–0.99 | — |
| max_megapixels | FLOAT | 2.00.5–10 | Max resolution for VITMatte processing. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| text_output | STRING | Text output from the model |
| masks | MASK | Generated segmentation masks |