Sa2VA Image Segmentation

XJSa2VAImageSegmentation

Sa2VA (Segment Anything 2 with Vision Assistant) provides high-quality image segmentation using text prompts. This node generates precise masks for objects described in your text prompt, with optional morphological refinement for cleaner results.

Pack: ComfyUI-Sa2VA-XJ

custom_nodes.ComfyUI-Sa2VA-XJ

Inputs (11)

Name	Type	Required
model_name	COMBO	required
image	IMAGE	required
segmentation_prompt	STRING	required
threshold	FLOAT	required
use_8bit	BOOLEAN	required
use_flash_attn	BOOLEAN	required
unload	BOOLEAN	required
morph	COMBO	required
erode_kernel	INT	required
dilate_kernel	INT	required
iterations	INT	required

Outputs (2)

Name	Type
text_output	STRING
masks	MASK