Full pipeline toolkit from raw footage to trained LoRA checkpoint. Early release, building in the open.<ul><li>WAN 2.1 + 2.2 (T2V and I2V)</li><li>Scene detection, captioning, validation, pre-encoding, training — all in one place</li><li>Phased training for multi-stage runs and WAN 2.2 MoE expert specialization</li><li>Data prep tools work standalone with any trainer (kohya, ai-toolkit, etc.)</li><li>RunPod + local GPU support</li><li>LTX coming next</li></ul>http://github.com/alvdansen/flimmer-trainerBuilt by Alvdansen Labs. Early release — actively fixing bugs, feedback welcome.

Flimmer — open source video LoRA trainer for WAN 2.1 + 2.2

Full pipeline toolkit from raw footage to trained LoRA checkpoint. Early release, building in the open.WAN 2.1 + 2.2 (T2V and I2V)Scene detection, captioning, validation, pre-enco…