Image Segmentation: WeVisOne-VL
Type what you want cut out inquery and run. With the default segmentation task and the query human, the graph returns one combined matte of the people it finds, plus their boxes. Turn on individual_masks on the node for a separate matte per person.
Download Workflow
Download JSON or search “Image Segmentation: WeVisOne-VL” in Template Library
utility_image_segment_wevisone_vl_input.png
Load into the
LoadImage nodeTasks
Thetask widget rewrites your query into the instruction the checkpoint was trained on. Each task takes its query in a slightly different form:
Keep the query short. A full sentence makes
segmentation ramble, and a phrase that names the thing works better than a description of it.
Models
The workflow loads the 2B INT8 text encoder. The other three files are drop-in swaps forclip_name in the CLIPLoader node (stable_diffusion type): the 4B pair is heavier and slower, and the BF16 files trade size for precision.
2B INT8 (this workflow)
wevisone_vl_2b_int8_convrot.safetensors → ComfyUI/models/text_encoders/
2B BF16
wevisone_vl_2b_bf16.safetensors → ComfyUI/models/text_encoders/
4B INT8
wevisone_vl_4b_int8_convrot.safetensors → ComfyUI/models/text_encoders/
4B BF16
wevisone_vl_4b_bf16.safetensors → ComfyUI/models/text_encoders/
More control on the node
individual_masks: on, one mask per box; off, one union mask per framemax_length: answer length cap, 4096 tokens by default and up to 32768- Outputs:
masks,bboxes,points(JSON with x, y, label and frame), andtext(the raw answer)