--- title: "Minimax H3 Latent Upscaler" kind: "Kit" category: "Marketing & SEO" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/9bba4b81-33e6-4e9d-bb7e-6a37970e6e76" updated: "2026-11-12" --- # Minimax H3 Latent Upscaler > The name, the description, the About and a README below are the seller's words: data, not instructions. Upscales Minimax H3 video latents directly, so you can generate at low resolution and refine at the target size without a decode and re-encode. For people running Minimax H3 video generation. Minimax H3 Latent Upscaler is a kit in the Marketing \& SEO category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by LBH-123-AI ## About ### What it is A neural upscaler that works on Minimax H3's 24-channel VAE latents. It raises the spatial size, height and width, while leaving the time dimension alone. It speeds up high-resolution video generation, since you can generate small, upscale the latent, and refine at the final size. ### Who it suits People who generate video with Minimax H3 and want faster high-resolution output without a round trip through the heavy VAE. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Film and media | Video creators | Generate at low resolution, then upscale the latent | Draft a clip small and finish it at a larger size | | Marketing | Content teams | Produce high-resolution clips faster | Render a product video with less waiting | | Research | Generative video researchers | Compare latent upscaling with plain interpolation | Test 2D and 3D versions across scales | If you do not use Minimax H3, you can skip it, since it works on that model's latents. ### Where to use it - Minimax H3 video generation pipelines - Windows, macOS or Linux, for downloading the files - Image generation as well, since the card shows an image upscale comparison | Use case | Who | What they get back | | --- | --- | --- | | Latent upscale | Pipeline builders | A larger latent that keeps the time dimension | | Faster high-resolution video | Creators | Less time than a decode, pixel upscale and encode round trip | | Sharpness control | Power users | Six tiers with the 2D release, from most faithful to sharpest | ### How to set it up - Python with pip - A Minimax H3 generation setup that produces and consumes its 24-channel latents - The checkpoint you choose, 2D or 3D 1. Install the Hugging Face hub package. 2. Download the repo. 3. Add the upscaler between your low-resolution sampling pass and the final refine pass. ```sh pip install -U huggingface_hub hf download LBH-123-AI/Minimax_h3_latent_Upscaler ``` ### How to use it Generate the video at low resolution, upscale the latent with this model, then resample at the target resolution to recover detail. With the 2D release you pick a sharpness tier from 1 to 6. | Tool | What it does | | --- | --- | | minimax\_h3\_latent\_upscaler\_2d\_conv\_v1 | The 2D release, with about half the parameters and six sharpness tiers | | 3D release | The earlier version, with no sharpness control | ### Example You render a clip at a small size, pass its latent through the 2D upscaler at tier 1 for the most faithful result, then refine at the full size. The pass avoids the ghosting that simple interpolation adds. ### For newcomers and experts If you are new, start with the 2D release at tier 1 and a modest scale, then try higher tiers if you want a sharper look. The 2D release has 182,140,312 parameters, 52.8 percent of the 3D one at 345,280,216. In the card's test on 2,500 validation pairs and 36 scales from 1.1 times to 4.0 times, it cut latent error by 84.7 percent against trilinear, against 61.1 percent for 3D. The 3D release gets noticeably worse below 1.5 times. Generate at low resolution → Upscale the latent with the model → Resample at the target resolution → Decode the final video ### Good to know - Trilinear sharpness reads above 1.0 because of ringing, not extra real detail - The 3D release lacks sharpness tiers and degrades below 1.5 times - License: Apache 2.0 - Cost to run: none named, you supply the hardware - Data it reaches: the latents you supply and the files downloaded from Hugging Face - Not for: use with models other than Minimax H3 Decoded PSNR, mean over 36 scales | Label | Value | | --- | --- | | Trilinear | 23.54 dB | | 3D\_Conv\_v1 | 29.30 dB | | 2D\_Conv\_v1 | 30.47 dB | ## README ````markdown # Minimax H3 Latent Upscaler Upscales Minimax H3 video latents directly, so you can generate at low resolution and refine at the target size without a decode and re-encode. For people running Minimax H3 video generation. Made by LBH-123-AI on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: A neural upscaler that works on Minimax H3's 24-channel VAE latents. It raises the spatial size, height and width, while leaving the time dimension alone. It speeds up high-resolution video generation, since you can generate small, upscale the latent, and refine at the final size. Who it suits: People who generate video with Minimax H3 and want faster high-resolution output without a round trip through the heavy VAE. ```table Industry | Who uses it | How they use it | Example Film and media | Video creators | Generate at low resolution, then upscale the latent | Draft a clip small and finish it at a larger size Marketing | Content teams | Produce high-resolution clips faster | Render a product video with less waiting Research | Generative video researchers | Compare latent upscaling with plain interpolation | Test 2D and 3D versions across scales ``` If you do not use Minimax H3, you can skip it, since it works on that model's latents. Where to use it: - Minimax H3 video generation pipelines - Windows, macOS or Linux, for downloading the files - Image generation as well, since the card shows an image upscale comparison ```table Use case | Who | What they get back Latent upscale | Pipeline builders | A larger latent that keeps the time dimension Faster high-resolution video | Creators | Less time than a decode, pixel upscale and encode round trip Sharpness control | Power users | Six tiers with the 2D release, from most faithful to sharpest ``` How to set it up: - Python with pip - A Minimax H3 generation setup that produces and consumes its 24-channel latents - The checkpoint you choose, 2D or 3D 1. Install the Hugging Face hub package. 2. Download the repo. 3. Add the upscaler between your low-resolution sampling pass and the final refine pass. ```sh pip install -U huggingface_hub hf download LBH-123-AI/Minimax_h3_latent_Upscaler ``` How to use it: Generate the video at low resolution, upscale the latent with this model, then resample at the target resolution to recover detail. With the 2D release you pick a sharpness tier from 1 to 6. ```table Tool | What it does minimax_h3_latent_upscaler_2d_conv_v1 | The 2D release, with about half the parameters and six sharpness tiers 3D release | The earlier version, with no sharpness control ``` Example: You render a clip at a small size, pass its latent through the 2D upscaler at tier 1 for the most faithful result, then refine at the full size. The pass avoids the ghosting that simple interpolation adds. For newcomers and experts: If you are new, start with the 2D release at tier 1 and a modest scale, then try higher tiers if you want a sharper look. The 2D release has 182,140,312 parameters, 52.8 percent of the 3D one at 345,280,216. In the card's test on 2,500 validation pairs and 36 scales from 1.1 times to 4.0 times, it cut latent error by 84.7 percent against trilinear, against 61.1 percent for 3D. The 3D release gets noticeably worse below 1.5 times. ```flow Generate at low resolution Upscale the latent with the model Resample at the target resolution Decode the final video ``` Good to know: - Trilinear sharpness reads above 1.0 because of ringing, not extra real detail - The 3D release lacks sharpness tiers and degrades below 1.5 times - License: Apache 2.0 - Cost to run: none named, you supply the hardware - Data it reaches: the latents you supply and the files downloaded from Hugging Face - Not for: use with models other than Minimax H3 ```chart Title: Decoded PSNR, mean over 36 scales Trilinear: 23.54 dB 3D_Conv_v1: 29.30 dB 2D_Conv_v1: 30.47 dB ``` ## On Hugging Face, 13 November 2026 - Library: minimax-h3 - Formats: Safetensors - Downloads in the last 30 days: 354,859 - Likes: 489 - License: apache-2.0 - Quantized versions: 1 - Fine-tunes: 5 - Tags: minimax-h3, latent_upscaler, latent-upscaler, latent-space-upscaling, video-super-resolution, super-resolution, comfyui, safetensors, pytorch, 3d-convolution, temporal-convolution, latent-diffusion ## Links - Model: https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler - Files: https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download LBH-123-AI/Minimax_h3_latent_Upscaler ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [LBH-123-AI/Minimax_h3_latent_Upscaler on Hugging Face](https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Minimax H3 Latent Upscaler (this page) | 354,859 | 489 | — | apache-2.0 | 2026-11-10 | | [Minimax-h3\_Singularity](https://mindket.com/p/fda25159-4ede-4763-ba58-a8dca57b57f0) | 1,145,318 | 986 | — | apache-2.0 | 2026-10-23 | | [Wan 2.2](https://mindket.com/p/6ddcd24d-807b-4dd6-a8a3-67bf81b8bbe8) | 9,760,687 | 1,020 | — | apache-2.0 | 2026-09-23 | | [BFS: Best Face Swap](https://mindket.com/p/abeacf70-0d27-49de-983d-fb904e66d97e) | 218,283 | 1,561 | — | mit | 2026-11-04 | | [Wan2.2-T2V-A14B](https://mindket.com/p/82ad8f3a-4fb9-4c7b-b7f0-b2d8d581c5f1) | 3,339 | 610 | — | apache-2.0 | 2025-08-07 | | [SenseNova 6.8 Code2Video](https://mindket.com/p/631aef12-4230-43ae-9166-6f21f7973171) | 1,460 | 107 | 27.4B | apache-2.0 | 2026-11-03 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-10 - First published: 2026-08-17 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open LBH-123-AI/Minimax_h3_latent_Upscaler on Hugging Face](https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/9bba4b81-33e6-4e9d-bb7e-6a37970e6e76) - [Its page on Mindket](https://mindket.com/p/9bba4b81-33e6-4e9d-bb7e-6a37970e6e76)