ComfyUI model file · Latent upscale model (fine-tune)

h3_upscaler_lms_v0.1.safetensors

H3 Upscaler LMS v0.1 · Sharpness-tuned latent upscaler for MiniMax H3

This is an experimental fine-tune of the MiniMax H3 3D latent upscaler by Alissonerdx, trained for 2,000 steps on the same sharpness data as his LMS LoRA. Put it in ComfyUI/models/latent_upscale_models and select it in the Minimax H3 Latent Upscaler (3D) node.

  • MiniMax H3
  • Latent upscale
  • 691 MB
  • fp16

This is the recommended fp16 file. The _fp32 file in the same folder is the training artifact, twice the size, and not needed for normal use.

h3_upscaler_lms_v0.1.safetensors

Type
Latent upscale model (fine-tune)
Format
Safetensors · fp16
Size
691 MB (690,593,048 bytes)
SHA256
40d42282…259e40d59
ComfyUI folder
models/latent_upscale_models/
Loader node
Minimax H3 Latent Upscaler (3D)
SHA256 and size from Hugging Face file metadata (Alissonerdx/Minimax-H3-ComfyUI), checked by RunComfy on .

The short version

What is h3_upscaler_lms_v0.1.safetensors?

Alissonerdx started from LBH-123-AI’s minimax_h3_latent_upscaler_3d_fp16 and fine-tuned it on a sharpness dataset, the one behind his minimax_h3_lms LoRA. The goal is latent upscaling that also adds crisp detail.

He calls it a research checkpoint: it can improve perceived detail, but it does not rebuild text, logos or fine structure that are already missing. Because the architecture is unchanged, it loads in the same 3D upscaler node as the original.

Install

Download and install h3_upscaler_lms_v0.1.safetensors

Where it goes
ComfyUI/
└─ models/
   ├─ …
   └─ latent_upscale_models/
      └─ h3_upscaler_lms_v0.1.safetensors
terminal · Linux / macOS
$ cd ComfyUI/models/latent_upscale_models$ wget -O h3_upscaler_lms_v0.1.safetensors \$   https://huggingface.co/Alissonerdx/Minimax-H3-ComfyUI/resolve/main/latent_upscaler/h3_upscaler_lms_v0.1.safetensors$ sha256sum h3_upscaler_lms_v0.1.safetensors# 40d4228227146245ef2b65480b647c50222465ca125de5880f192e3259e40d59

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 h3_upscaler_lms_v0.1.safetensors in ComfyUI

The upscaler works on latents, between a low-resolution H3 pass and a refining pass at the target size. The Minimax H3 Latent Upscaler (3D) node loads the file and upscales in one step.

Minimax H3 Latent Upscaler (3D) comes from the Comfyui_Minimax_h3_latent_Upscaler custom node pack. Install it with ComfyUI Manager first.

KSampler (low-res pass)

LATENT

Minimax H3 Latent Upscaler (3D)

model_nameh3_upscaler_lms_v0.1.safetensors

scale1.5–2.0

precisionfp16

MinimaxH3LatentUpscaler3D

KSampler (refine pass)

denoise0.3–0.5

Minimal graph. Click a node to open its reference page.
  • Why latent upscaling

    It skips the decode → pixel upscale → encode round trip through H3’s large video VAE.

  • Scales

    The 3D model was trained at 2×, 2.25×, 2.5× and 4×; its author reports weaker results below 1.5×.

Works with

Files a MiniMax H3 video workflow needs

h3_upscaler_lms_v0.1.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 h3_upscaler_lms_v0.1.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.

  1. Uses another version of this file1
  2. Uses other MiniMax H3 models3

Uses another version of this file

1 workflow

These workflows load a different precision or format of the same model. Select h3_upscaler_lms_v0.1.safetensors in their Minimax H3 Latent Upscaler (3D) node to use this version.

Uses other MiniMax H3 models

3 workflows

These workflows load another MiniMax H3 model. Select h3_upscaler_lms_v0.1.safetensors in their Minimax H3 Latent Upscaler (3D) node to use it instead.

Compare

Same file, other names, and alternatives

FileRelationSizeBest for
h3_upscaler_lms_v0.1.safetensorsThis page · fp16691 MBNormal inference
h3_upscaler_lms_v0.1_fp32.safetensorsSame model · fp32 training artifact1.38 GBArchival; not needed in ComfyUI
minimax_h3_latent_upscaler_3d_fp16.safetensorsBase model · LBH-123-AI691 MBFaithful upscaling without extra sharpening

Troubleshoot

Common errors and fixes

Value not in list: model_name: 'h3_upscaler_lms_v0.1.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/latent_upscale_models. Usually the file is missing, sits in a different folder.

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

Missing node type: MinimaxH3LatentUpscaler3D

Why: Minimax H3 Latent Upscaler (3D) is not built into ComfyUI. It comes from the Comfyui_Minimax_h3_latent_Upscaler custom node pack.

Fix: Install Comfyui_Minimax_h3_latent_Upscaler 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 690,593,048 bytes and that its SHA256 matches the value above. Download it again from Hugging Face · Alissonerdx/Minimax-H3-ComfyUI if not.

Rather skip the setup?

Run MiniMax H3 Action Scenes in your browser on a cloud GPU. Nothing to download.

Run MiniMax H3 online

FAQ

h3_upscaler_lms_v0.1.safetensors FAQ

fp16 or fp32?

fp16. The author recommends it for the included workflows and normal inference; fp32 is kept only as the full-precision training file.

Where do I put h3_upscaler_lms_v0.1.safetensors in ComfyUI?

In ComfyUI/models/latent_upscale_models/. Then refresh the node list or restart ComfyUI so Minimax H3 Latent Upscaler (3D) lists the file.

Which ComfyUI node loads h3_upscaler_lms_v0.1.safetensors?

Minimax H3 Latent Upscaler (3D). It comes from the Comfyui_Minimax_h3_latent_Upscaler custom node pack, so install that first.

Can I use h3_upscaler_lms_v0.1.safetensors commercially?

The repo’s custom LoRA licenses do not cover this upscaler; it keeps the terms of the model it was fine-tuned from, LBH-123-AI’s Apache-2.0 latent upscaler. The MiniMax H3 base model keeps its own license.

Sources: Alissonerdx/Minimax-H3-ComfyUI · Latent upscaler notes

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.