---
title: "Alibaba's MiniMax-H3-Fun-Controlnet-Union Steers Video Generation With One 6.8 GB Checkpoint"
subtitle: "Alibaba PAI drops a single ControlNet-Union checkpoint that adds Canny, Depth, HED, MLSD, Pose and inpainting to MiniMax-H3 video generation."
url: "https://alphasignal.ai/news/alibaba-s-minimax-h3-fun-controlnet-union-steers-video-generation-with-one-6-8"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-08-24T03:18:07.000Z"
updated: "2026-08-27T19:59:01.089Z"
type: "Model"
topics:
  - "Video"
  - "Open Source"
subtopics:
  - "Video Generation"
  - "Video Editing"
upvotes: 357
source_url: "https://huggingface.co/alibaba-pai/MiniMax-H3-Fun-Controlnet-Union"
comments: 0
truncated: true
---

# Alibaba's MiniMax-H3-Fun-Controlnet-Union Steers Video Generation With One 6.8 GB Checkpoint

> Alibaba PAI drops a single ControlNet-Union checkpoint that adds Canny, Depth, HED, MLSD, Pose and inpainting to MiniMax-H3 video generation.

Alibaba's PAI team just plugged a big hole in the MiniMax-H3 video model ecosystem. They released [MiniMax-H3-Fun-Controlnet-Union](https://huggingface.co/alibaba-pai/MiniMax-H3-Fun-Controlnet-Union), a single 6.81 GB safetensors checkpoint that steers H3 video generation with edge maps, depth maps, human poses, and more, without swapping models between conditions.

If you have been using MiniMax-H3 for text-to-video or image-to-video and wanted the kind of structural control that ControlNet gave you on image models, this is the missing piece.

## One checkpoint, five control signals

The headline feature is the Union design. A single checkpoint conditions the MiniMax-H3 video generator on Canny, Depth, HED, MLSD, or Pose control videos, and also runs video inpainting, with no per-condition checkpoint switching. That saves a lot of disk and VRAM juggling compared to shipping one ControlNet per modality.

The supported control signals cover most of what people actually reach for in video work:

* **Canny** for hard edge outlines from a reference clip
* **Depth** for preserving 3D scene structure and camera motion
* **HED** for softer, painterly edge guidance
* **MLSD** for straight line and architectural structure
* **Pose** for driving characters with human skeleton keypoints
* **Inpainting** for masked region regeneration inside a video

## How the control branch actually attaches

Rather than duplicating the whole transformer like the original image ControlNets did, this one is surgical. The control branch attaches to 5 of the 50 transformer blocks (layers 0, 10, 20, 30, 40), and every control skip is added to the main branch through a zero-gated projection. That is why the checkpoint is only 6.8 GB instead of a full copy of the base weights.

The zero-gated projection is the classic ControlNet trick, where the injection layers start at zero so the base model behaves normally at initialization and gradually learns to accept guidance during training. Here it is applied at just five evenly spaced depths through the 50-block stack.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [MiniMax-H3-Fun-Controlnet-Union model card](https://huggingface.co/alibaba-pai/MiniMax-H3-Fun-Controlnet-Union)
- [VideoX-Fun GitHub repository](https://github.com/aigc-apps/VideoX-Fun)
- [Awesome MiniMax-H3 index](https://github.com/wildminder/awesome-minimax-H3)
- [MiniMax H3 Acc LoRA writeup](https://comfyui-wiki.com/en/news/2026-08-26-minimax-h3-pdd-acc-lora)
- [FLUX.2-dev-Fun-Controlnet-Union model card](https://huggingface.co/alibaba-pai/FLUX.2-dev-Fun-Controlnet-Union)