Sign In

Minimax SEED HUNTER Workflow - Latent Upscaler + Seamless Video Continuation + Speedups

Updated: Aug 29, 2026

assetsseedhunterh3

Download

1 variant available

Config Other

Minimax Seed Hunter v1.2.1.json

291.83 KB

Verified:

Type
Workflows
Stats

957

Reviews
Published

Aug 28, 2026

Base Model

MiniMax H3

Hash
AutoV2
3D96E1BBFB
default creator card background decoration
Followers - 626

626

Likes - 1394

1.4K

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

https://huggingface.co/lightx2v/Minimax-h3-Turbo/blob/main/minimax_h3_fl2v_turbo_8step_v1.0_768p_comfyui_bf16.safetensors

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!)

https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_video_vae_int8_convrot.safetensors

Everything else should be easily available from the ComfyUI-manager Install Missing Nodes screen!