# ladaapp/lada

Restore videos with pixelated/mosaic regions

Repository: https://github.com/ladaapp/lada
Canonical: https://ross.abutalabs.com/products/lada
Homepage: https://codeberg.org/ladaapp/lada
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: depixelization, mosaic-removal, jav-restoration
Last push: 2026-02-27T07:23:28+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 69, release rhythm 69, longevity 48
- inputs: {"age_days": 673, "days_push": 187, "days_rel": 205, "gap_med": 7, "n_releases_24m": 26}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5702, forks 612 (observed 2026-08-28T04:09:28.095351+00:00)

## What it is
Lada is an open-source tool with both GUI and CLI that restores pixelated/mosaic regions in videos, primarily targeting JAV (Japanese adult video) content, using deep learning models. It supports real-time playback of restored video or export to file, running on NVIDIA, Intel Arc, and Apple Silicon GPUs.

## Use cases
- remove mosaic from jav videos
- restore pixelated video scenes
- depixelate censored video regions
- export restored video files
- watch restored videos in real time
- batch restore videos from the command line

## When to choose
- you need to remove mosaic/pixelation from adult videos
- you have a GPU with 4-6GB+ VRAM
- you want both a GUI player and a CLI for batch processing
- you want a free, self-hosted alternative to paid mosaic-removal services

## When to avoid
- you need general-purpose video enhancement or upscaling of non-mosaic content
- you have no GPU (CPU performance is impractically slow)
- you need guaranteed artifact-free results (quality varies by scene)
- you want to process non-video images

## Facets
- artifact type: application
- maturity: active
- function: video-processing, image-processing, machine-learning, deep-learning, cli, gui
- domain: machine-learning, media, computer-vision
- platform: windows, python, cross-platform
- tags: depixelization, mosaic-removal, video-restoration, jav, flatpak, adult-content, video, linux, macos, docker, gpu

## Member repositories
- ladaapp/lada (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.095351+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:53:33.976256+00:00, confidence not recorded.
  - readme: https://github.com/ladaapp/lada (fetched 2026-08-28T04:09:28.095351+00:00, sha 46f5f4117dae)
  - homepage: https://codeberg.org/ladaapp/lada (fetched 2026-08-29T08:49:24.077614+00:00, sha c6d02d15d241)
  - site_page: https://docs.codeberg.org/getting-started/what-is-codeberg (fetched 2026-08-29T08:49:24.080419+00:00, sha fe3047f34c81)
  - site_page: https://docs.codeberg.org/getting-started/faq (fetched 2026-08-29T08:49:24.082569+00:00, sha 7ffd1ab1d66b)
  - site_page: https://codeberg.org/ladaapp/lada/src/branch/main/docs (fetched 2026-08-29T08:49:24.088908+00:00, sha b1e458d5b059)
  - site_page: https://codeberg.org/ladaapp/lada/releases (fetched 2026-08-29T08:49:24.084664+00:00, sha deb8c57375ab)
  - site_page: https://codeberg.org/ladaapp/lada/commit/eb09e6b3b34d2c70c39a2a99c65b92156880a5f7 (fetched 2026-08-29T08:49:24.087262+00:00, sha b1e458d5b059)
  - site_page: https://codeberg.org/ladaapp/lada/commit/9ad8111005096b2f9e4a3f5f531be603422aeff3 (fetched 2026-08-29T08:49:24.090475+00:00, sha b1e458d5b059)
  - site_page: https://codeberg.org/ladaapp/lada/commit/3c40457d1ecd4fbb44a1419fbe8d1dd8a5bd8647 (fetched 2026-08-29T08:49:24.092002+00:00, sha b1e458d5b059)
  - site_page: https://codeberg.org/ladaapp/lada/commit/51b2f03a72ed68efe48d181f5be9a40ac9d2a07b (fetched 2026-08-29T08:49:24.093488+00:00, sha b1e458d5b059)
- Data as of 2026-08-30T08:39:29.467469+00:00.