LightX2V releases updated Turbo LoRA for MiniMax H3
LightX2V released an updated Turbo LoRA for MiniMax H3, enabling 8-step video generation in ComfyUI. Users report Ref2V works with the TurboSampler node, sigma shift 12/3, and 6 steps.
How this story unfolded
5 days · 0 reports · 3 community posts · from Aug 6
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Robotic systems struggle with physical navigation in recent demonstrations
- ChatGPT Visualize skill turns notes into interactive interfaces
- Twitch streamers sue Twitch, Amazon over AI training data use
- Fastino launches GLiNER2.5 with boundary-prediction architecture
- NVIDIA Sol Engine cuts MiniMax H3 latency to 14.93s