LightX2V releases MiniMax H3 Turbo LoRA for faster video gen

LightX2V released 4-step and 8-step Turbo LoRAs for MiniMax H3, cutting a 15-second 1MP clip from ~20 to ~11 minutes on an RTX 4090. ComfyUI-compatible versions are available via drbaph and QrusherZA.
How this story unfolded
3 weeks · 2 reports · 11 community posts · 13 of 14 shown
- Aug 6
- Aug 7
- Aug 10
- Aug 11
- Aug 12
- Aug 13
- Aug 23
- Aug 27
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Agentic Cloud concept introduced
- OpenAI's Codex client reveals GenUI interface platform
- Weaviate 1.39 adds Boost API, MMR, 4-bit quantization
- JPMorgan leads $5B debt package for Volta AI data centers
- Vercel Chat SDK adds Claude Managed Agents and Notion adapter