---
title: Minimax_h3_latent_Upscaler
canonical_url: "https://www.modelscope.cn/models/LBH-123-AI/Minimax_h3_latent_Upscaler"
md_url: "https://www.modelscope.cn/models/LBH-123-AI/Minimax_h3_latent_Upscaler.md"
repository: LBH-123-AI/Minimax_h3_latent_Upscaler
last_updated: 2026-09-17
license: apache-2.0
model_type:
- latent_upscaler
parameters: 690.6M
tensor_type:
- BF16
- F16
library_name:
- safetensors
- pytorch
frameworks:
- pytorch
downloads: 3593
stars: 13
tags:
- latent-upscaler
- latent-space-upscaling
- minimax-h3
- video-super-resolution
- super-resolution
- comfyui
- safetensors
- pytorch
- 3d-convolution
- temporal-convolution
- latent-diffusion
---
# Minimax_h3_latent_Upscaler
> Minimax_h3_latent_Upscaler - LBH-123-AI 在 ModelScope 开源的模型。Minimax H3 Latent Upscaler
LBH-123-AI/Minimax_h3_latent_Upscaler 是 ModelScope 魔搭社区上的 690.6M 参数机器学习模型，采用 apache-2.0 许可。
- **Repository**: LBH-123-AI/Minimax_h3_latent_Upscaler
- **License**: apache-2.0
- **Parameters**: 690.6M
- **Tags**: latent-upscaler, latent-space-upscaling, minimax-h3, video-super-resolution, super-resolution, comfyui, safetensors, pytorch, 3d-convolution, temporal-convolution, latent-diffusion
- **Downloads**: 3593
- **Stars**: 13
- **Last updated**: 2026-09-17
Source: https://www.modelscope.cn/models/LBH-123-AI/Minimax_h3_latent_Upscaler
---
English ·
中文
&color=blue&logo=huggingface)
# Minimax H3 Latent Upscaler
Neural latent-space upscaler for **Minimax H3** video generation. Works directly on Minimax H3's
**24-channel VAE latents** to upscale spatial resolution (H×W) while preserving the time dimension.
## Purpose
This model is designed to **accelerate high-resolution H3 video generation**:
1. Generate video at low resolution — far fewer latent tokens, much faster.
2. Upscale the latent in-place with this learned upscaler.
3. Re-sample / refine at the target resolution to recover detail.
By skipping the expensive `decode → pixel upscale → encode` round-trip through Minimax H3's
heavy ~5B-parameter VAE, this pipeline saves a significant amount of generation time. It also
avoids the **ghosting / double-image artifacts** that naive latent interpolation
(bilinear/bicubic) introduces.
## 📸 Examples
**Video upscale comparison** — click to play:
*(If the player doesn't render, [download the video here](https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler/resolve/main/examples/Minimax_h3_latent_Upscaler_001.mp4).)*
**Image upscale comparison**:
## Files in this repository
The current release is **v1**. Its three checkpoints live together in
[`minimax_h3_latent_upscaler_3d_conv_v1/`](/LBH-123-AI/Minimax_h3_latent_Upscaler/tree/main/minimax_h3_latent_upscaler_3d_conv_v1):
| File | Format | Precision | Size | Notes |
| :--- | :--- | :--- | :--- | :--- |
| `minimax_h3_latent_upscaler_3d_conv_v1/minimax_h3_latent_upscaler_3d_conv_v1_bf16.safetensors` | SafeTensors | bfloat16 | ~691 MB | Fastest on Ampere/Ada GPUs |
| `minimax_h3_latent_upscaler_3d_conv_v1/minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors` | SafeTensors | float16 | ~691 MB | Best speed / memory balance |
| `minimax_h3_latent_upscaler_3d_conv_v1/minimax_h3_latent_upscaler_3d_conv_v1_fp32.pth` | PyTorch | float32 | ~1.38 GB | Highest numerical accuracy |
All three checkpoints share the same **3D-convolution architecture**. Pick the precision that
matches your GPU and workflow.
`config.json` at the repository root is the **family index**: it records what every release shares
(the 24-channel H3 latent space and its normalization, the supported scale range, the ComfyUI node
mapping) and points to each released variant. The architecture spec for this release sits next to
the weights, in
[`minimax_h3_latent_upscaler_3d_conv_v1/config.json`](/LBH-123-AI/Minimax_h3_latent_Upscaler/blob/main/minimax_h3_latent_upscaler_3d_conv_v1/config.json):
24 in/out channels, 512 base channels, 12+12 blocks, temporal conv every 2 blocks with kernel size
5, 345,280,216 parameters.
The ComfyUI node infers the architecture from the state dict on load and does **not** read either
file — they are machine-readable specifications for downstream tooling.
### Versioning
Each release gets its own folder. New checkpoints will go to
`minimax_h3_latent_upscaler_3d_conv_v2/`, `..._v3/`, and so on, so older releases stay
downloadable and unchanged.
Filenames always carry the full release tag. The folder groups a release together for browsing,
but the filename is what actually identifies a checkpoint once it is on your disk — ComfyUI loads
every model from a single flat directory (`models/latent_upscale_models/`).
## Usage
Use with the companion ComfyUI custom node:
**[LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler](https://github.com/LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler)**
1. Install the custom node into `ComfyUI/custom_nodes/`.
2. Place the downloaded checkpoint in:
```text
ComfyUI/models/latent_upscale_models/
```
3. Add either **"Minimax H3 Latent Upscaler (2D)"** or **"Minimax H3 Latent Upscaler (3D)"**
from the `video/MinimaxH3` menu, connect a `LATENT`, pick the model, and set `scale`.
Supported upscale factors: **1.0× – 4.0×** (continuous, 0.1 step; default **2.0×**).
## Training Data
The model was trained on **~80,000 paired samples** (low-resolution latent + high-resolution target),
balanced across modalities and scale factors to maximize generalization.
- **~70,000** video pairs
- **~8,000** 2K image pairs
**Scale distribution (approximate):**
| Scale | Share | Purpose |
| :--- | :--- | :--- |
| 2× | 40% | Dominant real-world factor |
| 1.5× | 10% | — |
| 2.5× | 10% | — |
| 3× | 10% | — |
| 4× | 10% | — |
| 1.0×–4.0× (arbitrary decimals) | 10% | Generalization to any in-between scale |
## Architecture
3D-convolution backbone with temporal convolution and trilinear interpolation. The architecture
draws on and references the **LTX 2.3 Spatial Upscaler**
(`ltx-2.3-spatial-upscaler-x2-1.1.safetensors`) and the neural-latent-upscaling approach
pioneered by [Ttl / ComfyUi_NNLatentUpscale](https://github.com/Ttl/ComfyUi_NNLatentUpscale).
## License
Apache-2.0