[fork of] Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
Python · active 2026-01-05 → 2026-08-19 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 227 days from 2026-01-05 to 2026-08-19. Pushes: 10 total, peak 3 in a day. Pull requests: 10 total, peak 2 in a day. Issues: 67 total, peak 13 in a day. Comments: 102 total, peak 17 in a day. Stars: 1,983 total, peak 183 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| michaellightricks | 27 | 8 | 0 | 10 |
| rluxemburg | 19 | 0 | 0 | 5 |
| Copilot | 16 | 0 | 0 | 15 |
| rex-29 | 4 | 0 | 0 | 3 |
| kabachuha | 4 | 0 | 0 | 3 |
| q5sys | 4 | 0 | 1 | 3 |
| juntaosun | 4 | 0 | 0 | 2 |
| lt-research-bot | 4 | 1 | 3 | 0 |
| jaimitoes | 3 | 0 | 0 | 1 |
| jiaxiangc | 3 | 0 | 0 | 2 |
| crosson | 3 | 0 | 0 | 3 |
| FredyRivera-dev | 2 | 0 | 0 | 2 |
| hannalaguilar | 2 | 0 | 0 | 1 |
| Vickeyhw | 2 | 0 | 0 | 1 |
| biswas7122-commits | 2 | 0 | 0 | 2 |
| nalexand | 2 | 0 | 1 | 1 |
| 4suino | 2 | 0 | 0 | 0 |
| AlexeyKravtsov1987 | 2 | 1 | 0 | 0 |
| zwukong | 2 | 0 | 0 | 1 |
| amankumar812601-sys | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#2704suino2026-08-07 19:09[ltx-core] Prompt enhancement returns a repetition loop: inputs are right-padded before `generate()` on a decoder-only model
- Issue#2694suino2026-08-07 19:06[ltx-pipelines] `--enhance-prompt` is accepted and silently dropped by `ti2vid_two_stages`
- Pull request#2400xrjman2026-06-21 01:56
- Issue comment#199rluxemburg2026-05-29 18:25Different quality than the model on fal.ai
- Issue comment#211michaellightricks2026-05-12 15:06how to generate the trajectory video？
- Issue comment#141andzejsp2026-05-04 09:33Is AMD / ROCm support planned for LTX-2?
- Issue#202AmitMY2026-04-26 08:55VAE produces grid-like tile artifacts on flat regions (constant-green diagnostic)
- Issue#191wlike2026-04-11 04:22Relationship among models
- Issue comment#139xduzhangjiayu2026-04-09 09:34LTX2.3 embeddings_connector size mismatch
- Issue comment#141dougkersten2026-04-09 04:04Is AMD / ROCm support planned for LTX-2?
- Issue comment#146sahilshukla30032026-04-01 04:55CLI --quantization fp8-scaled-mm crashes with TypeError
- Issue#174seanhan19911990-source2026-03-23 20:32Feature Request : LTX-2 trainer Captioning tool
- Issue comment#165michaelforex2772026-03-21 12:24LTx2.3 train output noise, pls help
- Issue#171jlitz2026-03-20 19:21Controlling audio generation using batch processing Image to Video
- Pull request#169garrick992026-03-19 22:46
- Issue#167zappazack2026-03-18 21:581st test: the trainer is working under Windows 11. Any additional optimation suggestion?
- Issue comment#116DerekDenk2026-03-18 04:51AttributeError: 'Gemma3TextConfig' object has no attribute 'rope_local_base_freq' when running pipeline
- Issue comment#142chinaxunmei2026-03-12 01:52Wrong link to the Inpainting IC-Lora?
- Issue#157Binn372026-03-11 09:36Would you provide a command line of a2vid?
- Issue comment#142grimm11112026-03-10 03:12Wrong link to the Inpainting IC-Lora?
- Issue#150croviatrust2026-03-09 07:02📋 Documentation Enhancement Suggestion
- Issue#149zijieloooooou2026-03-09 06:32How to use ltx-2.3-temporal-upscaler-x2-1.0.safetensors?
- Issue#147jaimitoes2026-03-08 23:07Some testings in audio data preprocessing and improvements in latents checking
- Issue comment#147jaimitoes2026-03-08 23:07Some testings in audio data preprocessing and improvements in latents checking
- Issue#147jaimitoes2026-03-07 18:10Some testings in audio data preprocessing and improvements in latents checking
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,983 stars here means stars gained during the window, not the repo's star count.