ACut mirror: LaMa inpainting (ONNX)
Stable mirror of opencv/inpainting_lama (inpainting_lama_2025jan.onnx) for ACut logo / object removal on still images.
Upstream is derived from Carve/LaMa-ONNX / advimman/lama.
Try ACut
Privacy-first video editor for browser and desktop — local processing, captions, speech tools, and clean exports (no watermarks on the free tier):
Product: https://www.acutapp.com
Contents
inpainting_lama_2025jan.onnx— fixed 512×512 float32 image + mask inputs
License / attribution
Weights remain Apache-2.0 as published by OpenCV Zoo. Upstream: https://huggingface.co/opencv/inpainting_lama
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for vongocanhthi/acut-lama
Base model
opencv/inpainting_lama