Feyn Labs launches MultiMatte to keep the object you name and erase the rest

Shreyash Nigam and Hafedh Hichri fine-tuned 2.27% of Meta's SAM 3, preserving text prompts while replacing binary masks with alpha mattes.

By · Published · Updated

Primary source: Feyn Labs

Why it matters

MultiMatte shows the specialist-model strategy in concrete terms: update 2.27% of a foundation model, retain its language interface, and improve a narrow workflow. The commercial test is whether those gains survive independent evaluation with acceptable latency and cost.

A highly detailed mechanical dragonfly hovers in crisp focus, its intricate gears and glass wings perfectly separated from a softly dissolving garden background.

Feyn Labs founder and CEO Shreyash Nigam and software engineer Hafedh Hichri released MultiMatte on September 10th, a promptable image-matting model that keeps the object named by a user and removes everything else. A prompt such as "the dog," "the bowl," or "the jeans" can produce three different cutouts from the same photograph.…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.