Download
1 variant available
This checkpoint includes a config file, download and place it along side the checkpoint.
8530 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(67)
Aug 28, 2026
MiniMax H3
Fixed RIFE bug. Redownload if you have v1.2.0
Adds SEAMLESS VIDEO CONTINUATION, a very flexible tool for extending pre-existing videos. No new custom nodes.
Returns to Kijai's trusted Sol Attention (since SLA is basically the same thing now) -- so, one less custom node to download yay!
Show more

6240 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1.4K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
MiniMax H3 is licensed by MiniMax under the MiniMax H3 Community License Agreement. That agreement’s Applicable Territory excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America. Your use of H3 and of any H3 derivative is subject to that agreement and its Acceptable Use Policy.
MiniMax H3
This advanced filmmaker's workflow cleanly and quickly generates 3 low resolution sample preview gens, allowing you to select your favorite to then take to upscale finalization. The workflow has every feature an AI filmmaker could need, and easily produce the highest quality and resolution Minimax is capable of. It comes equipped with all quality of life features, the top known speed ups, and many options, from seamless video continuation to custom audio, to frame interpolation to go from 24 FPS to 48-60. Everything is here!
Quick reminder: 0.5 MP -> 2x upscale = 2.0 MP output. That's 4x the pixels. Most 24 GB or under cards will OOM if you try to gen 12-15 seconds at that resolution! This memory-hog of a model was built around 1.0 MP outputs (768p), after all.
I made this entire short film using this workflow alone!
Watch my tutorial video on how to use the workflow + a bunch of tips and tricks!
.: Load Image Node
https://github.com/obvpm/comfyui-obvpm (must be manually installed, unzipped folder into /custom_nodes/)
.: Latent Upscaler
- Node: https://github.com/LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler
- Latent Upscale Model: https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler/blob/main/minimax_h3_latent_upscaler_3d_bf16.safetensors
(put into /latent_upscale_models/ folder)
.: Sol-Attention (Speedup, works best at higher step counts 12+)
https://github.com/kijai/ComfyUI-SolAttn_triton
.: Turbo LoRA
Lightx2v's recommendation is to use euler/beta, with shift value option turned on at 6.0/3.0.
.: Audio/Video Loader node
https://github.com/WhatDreamsCost/WhatDreamsCost-ComfyUI
.: TaeH3 (for Kijai's Model Preview Override):
https://huggingface.co/Kijai/MiniMax-H3-TAE/blob/main/vae_approx/taeh3.safetensors
.: Kijai's int8 Video VAE (much faster than default!)
Everything else should be easily available from the ComfyUI-manager Install Missing Nodes screen!
