Skip to content

Lightricks/LTX-Video-Trainer

View on GitHub ↗Related repositories →

Finetuned multi shot video generation trainer for Lightricks' LTX Video model

Python · active 2025-03-222026-05-03 (UTC)

Partial coverage11,520 / 12,566 hourly files (92%) · 2 absent upstream · 1,042 failed, retryable2025-03-052026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
277
Pushes
7
Pull requests
7
Issues
19
Stars
180
Forks
23

Activity over time

Daily event counts in the loaded window

Line chart, 408 days from 2025-03-22 to 2026-05-03. Pushes: 7 total, peak 4 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 19 total, peak 2 in a day. Comments: 34 total, peak 5 in a day. Stars: 180 total, peak 8 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

Recent activity

Latest issues, pull requests and releases

  • Issue#66J1dan2026-01-26 08:55
    VRAM Requirements for LoRA Finetuning 13B model
  • Issue#65LSI862026-01-23 07:42
    Language fine-tune
  • Issue comment#59JusQD2026-01-02 08:43
    Preprocessing dataset with videos with too few frames can lead to incorrect labels
  • Issue#63J1dan2026-01-02 06:45
    [Discussion/Question] Weak Controllability on Training Set with LoRA Finetuning (POV Motion Dataset)
  • Issue comment#56JusQD2025-12-27 13:41
    validation image size
  • Issue#61fyting2025-12-17 08:09
    [Question] Guidance on training steps vs. dataset size for LoRA fine-tuning
  • Issue comment#54lenn-arts2025-11-04 15:50
    SEVERE: fix `main_media_paths` and `valid_video_paths` out of sync during filtering, causing condition-video misalignment
  • Issue#56BumbleStone2025-10-21 13:41
    validation image size
  • Pull request#52matanby2025-10-06 15:26
  • Pull request#52rluxemburg2025-09-29 15:27
  • Issue comment#32erenovic2025-09-29 09:04
    Training with keyframe conditioning
  • Issue#51zihaozou2025-09-24 14:38
    Model is hard to be modified
  • Issue#50ohad2042025-09-11 16:12
    i want to change the LTXVideoTransformer3DModel
  • Pull request#49oumad2025-09-06 14:47
  • Issue comment#3xylshawn2025-08-09 18:39
    Are there any plans to release VAE training code?
  • Issue comment#38pinballelectronica2025-08-07 01:57
    Fintuning distilled version
  • Issue comment#44YasheshSavani2025-07-22 22:01
    License request (MIT, Apache 2.0 etc)
  • Issue comment#44matanby2025-07-22 18:12
    License request (MIT, Apache 2.0 etc)
  • Issue comment#42matanby2025-07-22 15:24
    Problem when the dataset are images
  • Issue comment#40matanby2025-07-22 15:21
    Finetuning multi frame conditioning
  • Issue comment#46geezah2025-07-22 10:43
    Bug: Gradient Accumulation
  • Issue#46geezah2025-07-22 10:43
    Bug: Gradient Accumulation
  • Issue comment#37netefrat2025-07-21 09:53
    Loss Value
  • Issue#44YasheshSavani2025-07-16 18:21
    License request (MIT, Apache 2.0 etc)
  • Issue#42soshette72025-07-07 20:14
    Problem when the dataset are images

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 180 stars here means stars gained during the window, not the repo's star count.