Lightricks/LTX-2

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

61
/ 100
Established

Supports multiple inference pipelines including two-stage generation with spatial upscaling and single-stage modes, along with specialized LoRA adapters for motion tracking, pose control, and camera movements. Built on a Diffusion Transformer (DiT) architecture with Gemma-3 text encoding, the package includes spatial and temporal upscalers for resolution enhancement and integrates with HuggingFace model hosting for easy checkpoint management.

4,696 stars. Actively maintained with 4 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 22 / 25

How are scores calculated?

Stars

4,696

Forks

698

Language

Python

License

Last pushed

Mar 11, 2026

Commits (30d)

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Lightricks/LTX-2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.