MiniMax H3 SelfLift 2K QHD

AI-KSK ComfyUI workflow: MiniMax H3 SelfLift 2K QHD. The same SelfLift generation chain as the 768P preview, extended with SeedVR2 post upscaling to QHD 2560x1440.

Main features:
- MiniMax H3 hybrid FL2VA/Ref2VA INT8 UNET with Qwen3-VL 32B text encoder, video and audio VAEs for native audio generation.
- SelfLift 3D latent refinement with the MiniMax H3 latent upscaler and FL2V Turbo 4-step LoRA at 0.65 strength, 8-step Euler sampling.
- SeedVR2 3B FP8 video upscaling with block-swap VRAM optimization, normalized to QHD 2560x1440.
- Native audio preserved through the video/audio VAE decode, DLSS 2x frame interpolation (24 to 48 FPS).
- Balanced tier for publishing where 2K is the delivery target without 4K render cost.

Suggested workflow:
1. Import the JSON into ComfyUI and install the model files and custom nodes referenced by the workflow.
2. Provide the required text, image, or video inputs for the selected path.
3. Adjust resolution, steps, denoise, and prompt controls, then run the connected SaveVideo output.


RunningHub workflow:
https://www.runninghub.ai/zh-cn/post/2098787722725965826?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/BV1vFYz6HECU/

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