ComfyUI model file · Tiny VAE (preview decoder)

taeh3.safetensors

TAEH3 · Tiny AutoEncoder for MiniMax H3 · Fast preview decoder for MiniMax H3 sampling

taeh3.safetensors is madebyollin’s Tiny AutoEncoder for MiniMax H3. It decodes H3 latents into rough video previews while you sample, at a fraction of the full VAE’s cost. Put it in ComfyUI/models/vae_approx and pick it in a preview node such as KJNodes’ Model Preview Override.

  • MiniMax H3
  • Live preview
  • 22.7 MB
  • MIT

Kijai’s older 2D preview model is also called taeh3.safetensors but is a different file (9.8 MB). Check the size and SHA256 below.

taeh3.safetensors

Type
Tiny VAE (preview decoder)
Parameters
11.3M · fp16 · temporal decoder
Format
Safetensors · fp16
Size
22.7 MB (22,709,752 bytes)
SHA256
4fd022bf…1863d4c13
ComfyUI folder
models/vae_approx/
Loader node
Model Preview Override
License
MIT
SHA256 and size from Hugging Face file metadata, matching madebyollin/taehv commit 62f7591, checked by RunComfy on .

The short version

What is taeh3.safetensors?

Watching an H3 video take shape normally means decoding every preview through the 5-billion-parameter video VAE, which is too slow to do each step. TAEH3 is an 11.3M-parameter decoder trained by Ollin Boer Bohan (author of TAESD) to approximate that VAE. It turns latents into low-resolution previews quickly enough to update every couple of steps.

It is temporal: 5n+2 latent frames decode to 17n+5 video frames, the same frame count the full VAE produces, so previews play as motion rather than separate stills.

Two different files share this name. Kijai trained a quick 2D preview decoder first and also named it taeh3.safetensors (9.8 MB, SHA256 f0f60fa0…). Kijai now points to madebyollin’s version as the better one. Community packs rename Kijai’s file taeh3_2d_kijai.safetensors so both can live in the same folder.

Install

Download and install taeh3.safetensors

Where it goes
ComfyUI/
└─ models/
   ├─ …
   └─ vae_approx/
      └─ taeh3.safetensors
terminal · Linux / macOS
$ cd ComfyUI/models/vae_approx$ wget -O taeh3.safetensors \$   https://github.com/madebyollin/taehv/raw/62f7591f59dfbb4c3c02b7a621d180a9eeaba26c/safetensors/taeh3.safetensors$ sha256sum taeh3.safetensors# 4fd022bfcab08772fe0536b17ea1a3bbb5625be11e397868d1c5d891863d4c13

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

Use

How to load taeh3.safetensors in ComfyUI

TAEH3 does not touch your final video. It only decodes sampler previews. Model Preview Override from KJNodes reads it from models/vae_approx and patches the MODEL before your sampler.

Model Preview Override comes from the ComfyUI-KJNodes custom node pack. Install it with ComfyUI Manager first.

Load Diffusion Model

MODEL

Model Preview Override

tiny_vaetaeh3.safetensors

ModelPreviewOverrideKJ

KSampler

model●

previewlive RGB

Minimal graph. Click a node to open its reference page.
  • Turn previews on

    Set ComfyUI’s preview method to auto or TAESD so the sampler shows them.

  • Final output unchanged

    The full video VAE still decodes the result. TAEH3 only speeds up previews.

Works with

Files a MiniMax H3 video workflow needs

taeh3.safetensors is one part of the stack. A workflow that reports a missing model usually needs these too. Use the Ref2VA diffusion model instead of FL2VA for reference-to-video workflows.

FileRoleFolderSizeDownload
minimax_h3_fl2va_pruned_int8_convrot.safetensorsDiffusion model (FL2VA)models/diffusion_models/20.97 GB Get
qwen3vl_32b_minimax_h3_nvfp4_awq.safetensorsText encoder (Qwen3-VL 32B)models/text_encoders/15.69 GB Get
minimax_h3_video_vae_fp16.safetensorsVideo VAEmodels/vae/5.21 GB Get
minimax_h3_audio_vae_fp32.safetensorsAudio VAEmodels/vae/605 MB Get
minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_bf16.safetensorsTurbo LoRA, 4 steps(optional)models/loras/1.96 GB Get

Run it

ComfyUI workflows that can use taeh3.safetensors

We match workflows by the model files they load: this exact file first, then other versions of it, then workflows built for the same use, then other models from the same family.

Uses this exact file

2 workflows

These workflows already load taeh3.safetensors. Open one and run it as is.

Compare

Same file, other names, and alternatives

FileRelationSizeBest for
taeh3.safetensorsThis page · madebyollin, temporal22.7 MBSmooth video previews
taeh3_2d_kijai.safetensorsDifferent model · Kijai, 2D (also shipped as taeh3.safetensors)9.8 MBPer-frame stills; older setups
taeh3_decoder.safetensorsDifferent file · Civitai preview pack39.5 MBThe MiniMax H3 Preview Override custom node

Troubleshoot

Common errors and fixes

Value not in list: tiny_vae: 'taeh3.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/vae_approx. Usually the file is missing, sits in a different folder, or was saved under another name such as minimaxH3Preview_v10.safetensors.

Fix: Move the file into ComfyUI/models/vae_approx/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

Missing node type: ModelPreviewOverrideKJ

Why: Model Preview Override is not built into ComfyUI. It comes from the ComfyUI-KJNodes custom node pack.

Fix: Install ComfyUI-KJNodes with ComfyUI Manager (or git clone it into ComfyUI/custom_nodes), then restart ComfyUI.

SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 22,709,752 bytes and that its SHA256 matches the value above. Download it again from GitHub · madebyollin/taehv if not.

Rather skip the setup?

Run MiniMax H3 Long Video Generation in your browser on a cloud GPU. Nothing to download.

Run MiniMax H3 online

FAQ

taeh3.safetensors FAQ

I have two files called taeh3.safetensors. Which is which?

Check the size. 22,709,752 bytes (SHA256 starting 4fd022bf) is madebyollin’s temporal TAEH3 on this page. 9,791,388 bytes (starting f0f60fa0) is Kijai’s 2D version. They are different networks; keep both by renaming Kijai’s to taeh3_2d_kijai.safetensors.

Does TAEH3 change the final video?

No. It only decodes previews during sampling. Your output still goes through the full MiniMax H3 video VAE.

Where do I put taeh3.safetensors in ComfyUI?

In ComfyUI/models/vae_approx/. Then refresh the node list or restart ComfyUI so Model Preview Override lists the file.

Which ComfyUI node loads taeh3.safetensors?

Model Preview Override. It comes from the ComfyUI-KJNodes custom node pack, so install that first.

Can I use taeh3.safetensors commercially?

Yes. TAEH3 is released under the MIT license; keep the copyright notice if you redistribute it.

Sources: madebyollin/taehv on GitHub · OzzyGT/taeh3 mirror · Kijai/MiniMax-H3-TAE

RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.