Skip to content
ComfyUI Wiki · 工作流与开源创作分享·· 28 days agoPicksAI score71

taobao-content-ai releases MiniMax H3 Ref2VA acceleration LoRA and ComfyUI workflow

Image to video

AI briefing

taobao-content-ai released a Ref2VA acceleration LoRA for MiniMax H3, launching 8-step and 4-step PTD versions on October 20, and adding on October 22 an 8-step version trained with PTD plus RefAsymOPD, enabling reference image input with video and audio output.

Why it matters

Regarding the Ref2VA acceleration LoRA for MiniMax H3, the material provides weight specifications, ComfyUI node installation and VRAM thresholds, making it easier to judge whether it can be integrated into existing video production pipelines.

Open original comfyui-wiki.com