AI-KSK ComfyUI workflow: MiniMax H3 Larry Turbo 8 Step Ref2VA.

This workflow is the Larry Turbo 8-step reference-to-video benchmark route. It generates audio-attached video from a reference image using a turbo LoRA distilled for fast iteration, so you can screen prompts and motion quickly before spending render time on heavier schedules.

Main features:
- Reference-to-video generation with the MiniMax H3 Ref2VA INT8 model
- Qwen3-VL 32B MiniMax text encoder with video and audio VAEs
- minimax_h3_turbo_v4 step600 EMA turbo LoRA on the model path
- 8-step simple schedule wired to the connected sampler
- Audio-conditioned MiniMax H3 output saved as MP4 video

Suggested workflow:
Use this route as the fast baseline when judging a reference image plus prompt. Keep the reference face stable and describe motion in one sentence first, then raise prompt detail once identity and motion rhythm are stable.

RunningHub workflow (try online, no install needed):
https://www.runninghub.ai/zh-cn/post/2098339265314123777?inviteCode=rh-v1111

AI-KSK RunningHub workflow hub:
https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111

Bilibili tutorial:
https://www.bilibili.com/video/BV16DYL6FEsh/

RunningHub registration and AI tools:
https://www.runninghub.ai/?inviteCode=rh-v1111
https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111
https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111
https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111

Stable global access:
https://lelians.com/#/register?code=mFIJ5tZn

TokenRhythm AI model credits:
https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA

Youyun Cloud GPU:
https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq
https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52

RunPod Cloud GPU:
https://runpod.io/?ref=sxk5n5m7

Support AI-KSK:
https://ko-fi.com/aiksk