ComfyUI Node: LayerMask: SegmentAnythingUltra V2.1
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
😺dzNodes/LayerMask
Inputs
image IMAGE
sam_model
- sam_vit_h (2.56GB)
- sam_vit_l (1.25GB)
- sam_vit_b (375MB)
- sam_hq_vit_h (2.57GB)
- sam_hq_vit_l (1.25GB)
- sam_hq_vit_b (379MB)
- mobile_sam(39MB)
grounding_dino_model
- GroundingDINO_SwinT_OGC (694MB)
- GroundingDINO_SwinB (938MB)
threshold FLOAT
detail_method
- VITMatte
- VITMatte(local)
- PyMatting
- GuidedFilter
detail_erode INT
detail_dilate INT
black_point FLOAT
white_point FLOAT
process_detail BOOLEAN
prompt STRING
device
- cuda
- cpu
max_megapixels FLOAT
Outputs
IMAGE
MASK
Extension: HFDownLoad Node for ComfyUI
Download the model from huggingface and put it in any directory.
Authored by icesun963
Looking for a different node?
More nodes in HFDownLoad Node for ComfyUI
Other 😺dzNodes/LayerMask nodes
- LayerMask: BBox Join(Advance)
- LayerMask: Ben Ultra(Advance)
- LayerMask: BiRefNetUltra(Advance)
- LayerMask: BiRefNet Ultra V2(Advance)
- LayerMask: BlendIf Mask
- LayerMask: CreateGradientMask
- LayerMask: Draw BBox Mask(Advance)
- LayerMask: Draw BBox Mask V2(Advance)
- LayerMask: DrawRoundedRectangle
- LayerMask: EVF-SAM Ultra(Advance)
- LayerMask: Florence2 Ultra(Advance)
- LayerMask: Human Parts Ultra(Advance)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.