Video Generation - MiniMax H3 (Ref2VA)

What it does

MiniMax H3 turns a text prompt plus reference media into a short video clip with built-in synchronized stereo audio — no separate text-to-video and text-to-speech step, everything in one model. That's the headline capability.

CNAPS Studio deploys the omni-reference (Ref2VA) checkpoint. You write a prompt, attach a reference image and a reference video clip, and H3 uses them as guidance for subject, style, and — because the reference clip's soundtrack is read as well — voice timbre and sonic character. Output runs 5 – 15 seconds at 24 fps in one of six trained canvas sizes, from 21:9 widescreen to 9:16 vertical.

Note on the other checkpoint. MiniMax also publishes H3-Base-FL2VA (first-frame / last-frame / in-between animation). That checkpoint is not deployed in CNAPS Studio — the Video Generation node is Ref2VA only. If you need frame-to-frame animation, see the other models in the Video Generation lineup.

Problem it solves

• Video + audio in one shot — Most open-source video generators produce silent video. H3 generates the video and matching stereo audio (dialogue, sound effects, ambience, music) in the same forward pass — synchronized, no separate audio pipeline needed
• Reference-driven creative direction — Steer generation with mixed references: text describes the shot, an image anchors the subject or style, a video clip carries both motion/style reference and its soundtrack, which can act as a voice timbre reference so a generated character speaks in that voice
• Lip-sync without a second pass — Because picture and sound share one denoising loop, dialogue lands on the mouth movement rather than being aligned afterward
• Bilingual & multilingual dialogue — 11 languages officially supported (English, Chinese, Japanese, Korean, French, German, Italian, Spanish, Portuguese, Russian, Arabic) with additional partial support
• Up to ~14.4-second clips — Longer than most competing open video generators, useful for narrative shots rather than just 4–5 s micro-clips

Input/Output

Input

• Text prompt — describes the shot
• Reference image — subject / style / object anchor
• Reference video clip — motion and style reference; its own soundtrack is used as an audio reference

Upstream, the Ref2VA checkpoint accepts up to 9 reference images, 3 video clips and 3 audio clips (each 2 – 15 s, ≤ 15 s total per modality). Whether the CNAPS Studio node exposes more than one image and one video input is not confirmed here — verify against the node before documenting a higher limit.

Options

The node exposes four settings — three on the node itself, one under Advanced.

1. Clip length (5 – 15 s at 24 fps) — set in frames:

2. Canvas (W×H) — the model's six trained aspect ratios:

3. Diffusion steps (20 – 75) — default 50. More steps generally means more detail at the cost of generation time.

4. Random seed (Advanced Options) — -1 = random. Set a fixed value to reproduce a result.

Output

An MP4 video with a synchronized 32 kHz stereo audio track — matching the requested frame count and canvas size.

Performance & Deployment

2K path. MiniMax's H3-Regenerate-2K (native 2K regeneration) and H3-Context-IR (advanced prompt understanding) are hosted MiniMax API services, not part of the open-source release. They are not part of this node. Maximum output here is the canvas you select.

How MiniMax H3 compares

MiniMax H3 sits alongside the other video generators in CNAPS Studio's Video Generation lineup. Its distinguishing capability is video + synchronized native audio in one pass — most alternatives produce silent video and require a separate TTS or Foley step. Trade-offs: the community license carries commercial-use restrictions outside CNAPS Studio (see below), and the model is heavy enough that generation runs in minutes rather than seconds.

All models run inside CNAPS Studio — compare them side-by-side with the Video Compare tool.

License Note (Important)

• License: MiniMax H3 Community License Agreement — this is not an OSI-approved open license
• Regional availability: Using MiniMax H3 through CNAPS Studio is licensed for all regions — CNAPS holds an approved MiniMax individual license with no territorial restriction. If you instead download the open weights (e.g., from Hugging Face) and run them independently, the community license still restricts commercial use in the USA / EU / UK / South Korea, and you would need your own approved license from MiniMax via the application form
• Encoder license: The H3 text encoder reuses Qwen3-VL-32B, which is licensed under Apache 2.0 — that attribution applies to the encoder component
• Different from the rest of the lineup: These terms differ significantly from the Apache 2.0 / MIT licenses on Cosmos3-Nano, Wan2.2, and Helios; review the full agreement before relying on the model outside CNAPS Studio

Model Source

• Hugging Face

MiniMaxAI/MiniMax-H3 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.



huggingface.co


• HF Collection: MiniMax-H3 Collection — 46 items, includes LoRAs, quantizations, and finetunes
• GitHub: https://github.com/MiniMax-AI/MiniMax-H3
• API docs: MiniMax Platform
• Consumer app: Hailuo AI
• License: MiniMax H3 Community License Agreement
• License application form (USA/EU/UK/South Korea): https://platform.minimax.io/h3-license

Compliance & Provenance

For more on how we classify models and mark outputs, see our AI Policy.