ComfyUI Node: MatAnyone2
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
MatAnyone
Inputs
src_video IMAGE
mask_frame INT
n_warmup INT
foreground_mask IMAGE
foreground_MASK MASK
solid_color IMAGE
r_erode INT
r_dilate INT
max_internal_size INT
max_mem_frames INT
use_long_term BOOLEAN
Outputs
IMAGE
IMAGE
Looking for a different node?
Also provided by 2 other extensions
- Mat Anyone2 (QQ) — ComfyUI-WanVideoWrapper_QQWanVideoWrapper_QQ
Propagate a mask through video frames using MatAnyone2. video: Input video frames [B,H,W,C] mask: Starting frame mask (black and white) warmup_iterations: Number of refinement passes for first frame (0-10, default 5). Lower = faster but less accurate. force_cpu: If False, uses GPU if available. If True, forces CPU processing.
- MatAnyone2 — ComfyUI-MatAnyone2video/matting
More nodes in ComfyUI-MatAnyone
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.