wladradchenko/wunjo.wladradchenko.ru

Health v2 · maintenance only

Adoption not part of the score

1169 stars · 116 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Wunjo CE is an open-source, locally-run AI media suite for face swap, lip sync, voice cloning, object/text/background removal, restyling, and image-to-video or text-to-video generation. It ships as a desktop/web application with Docker support and a public API, built on diffusion models and Segment Anything.

Use cases

• swap faces in photos and videos locally
• generate lip-synced video from audio
• clone a voice from a short sample
• remove objects, text, or backgrounds from images
• generate video from text or a single image
• restyle photos and videos with diffusion models
• separate vocals from a music track
• run deepfake tools offline for free

When to choose

• you want free, local, offline AI video and image editing without cloud services
• you need face swap, lip sync, and voice cloning in one tool
• you want an API to automate media generation pipelines
• you have a GPU and want to avoid uploading personal media to third parties

When to avoid

• you need a lightweight tool without GPU hardware
• you want production-grade, polished commercial video editing
• you cannot install large ML model weights locally
• your use case is prohibited by deepfake ethics or local laws

Facets

application · maturity active

image-processing video-processing speech-recognition tts machine-learning deep-learning stable-diffusion audio-processing artificial-intelligence image-processing deep-learning media python cross-platform face-swap lip-sync deepfake voice-clone video-generation background-removal diffusion-models controlnet segment-anything local-ai photo-editing video-editing video audio docker gpu desktop web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wladradchenko/wunjo.wladradchenko.ru")