# rotemtzaban/STIT

Repository: https://github.com/rotemtzaban/STIT
Canonical: https://ross.abutalabs.com/products/stit
Language: Python
License: MIT
License Family: permissive
Last push: 2022-05-17T21:13:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1686, "days_push": 1569, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1197, forks 164 (observed 2026-08-28T04:03:57.311210+00:00)

## What it is
STIT (Stitch it in Time) is a research implementation of a GAN-based framework for semantic editing of faces in real videos, based on the paper 'Stitch it in Time: GAN-Based Facial Editing of Real Videos'. It leverages StyleGAN latent space alignment to produce temporally consistent facial manipulations in talking-head videos.

## Use cases
- edit faces in real videos with GANs
- apply semantic facial manipulations to talking head videos
- invert real video frames into StyleGAN latent space
- achieve temporally consistent video face editing
- reproduce the Stitch it in Time research paper
- run StyleCLIP-based edits on video frames

## When to choose
- you need temporally coherent facial editing of real videos
- you want a research-grade implementation of the STIT paper
- you work with StyleGAN inversion and video pipelines in PyTorch

## When to avoid
- you need a polished end-user video editing application
- you lack a CUDA GPU or don't want to manage pretrained model downloads
- you need actively maintained software with recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, video-processing
- domain: computer-vision, deep-learning, image-processing
- platform: python
- tags: gan, stylegan, face-editing, video-editing, research-code, temporal-consistency, stylegan-inversion, paper-implementation, video, gpu, linux

## Member repositories
- rotemtzaban/STIT (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.311210+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 2026-08-30T06:21:28.757550+00:00, confidence not recorded.
  - readme: https://github.com/rotemtzaban/STIT (fetched 2026-08-28T04:03:57.311210+00:00, sha 75768d79ef69)
- Data as of 2026-08-30T08:39:29.467469+00:00.