Nano Banana
MiniMax H3 — Open-Weight AI Video with Native Stereo Audio
MiniMax H3, released in August 2026, is an open-weight video model with native stereo audio and multimodal reference control. MiniMax describes it as Seedance-level quality, and it supports reference-to-video and multi-shot commercial creation.
- MiniMax H3 (open weights)
- Native stereo audio
- Up to 15 image, video or audio refs
- 768p and 2K
More models
- Veo 3.1GoogleText to video · Frames · Up to 4K · Up to 8s
- Veo 3.1 FastGoogleText to video · Frames · Up to 4K · Up to 8s
- Seedance 2.5ByteDanceText to video · Frames · References · Up to 720p · Up to 30s
- Seedance 2.0ByteDanceText to video · Frames · References · Up to 1080p · Up to 15s
- Seedance 2.0 FastByteDanceText to video · Frames · References · Up to 720p · Up to 15s
- Seedance 2.0 MiniByteDanceText to video · Frames · References · Up to 720p · Up to 15s
- Seedance 1.5 ProByteDanceText to video · Frames · Up to 1080p · Up to 12s
- Kling 3.0Kling AIText to video · Frames · References · Up to 1080p · Up to 30s
- Kling 2.6Kling AIText to video · References · Up to 1080p · Up to 30s
- Wan 3.0AlibabaText to video · Frames · References · Up to 1080p · Up to 15s
- Wan 2.7AlibabaText to video · References · Up to 1080p · Up to 15s
- Wan 2.6AlibabaText to video · Frames · References · Up to 1080p · Up to 15s
- MiniMax H3 MaxMiniMaxText to video · Frames · References · Up to 768P · Up to 15s
- MiniMax H3MiniMaxText to video · Frames · References · Up to 2K · Up to 15s
- Hailuo 2.3MiniMaxText to video · Frames · Up to 1080p · Up to 10s
- Hailuo 2.3 FastMiniMaxFrames · Up to 1080p · Up to 10s
- Gemini Omni 1.1 FlashGoogleText to video · Frames · References · Up to 4K · Up to 10s
- Grok Imagine VideoxAIText to video · Frames · Up to 720p · Up to 30s
- HappyHorse 1.1AlibabaText to video · Frames · Up to 1080p · Up to 10s
Why MiniMax H3 Is a Great AI Video Generator
MiniMax H3 combines strong quality with an open model you could also run yourself later. It suits commercials and multi-shot clips where you need to steer with many references.
Open weights
MiniMax released H3 as an open-weight model.
Stereo sound
Audio is generated natively in stereo with the video.
Reference control
Mix up to 15 images, clips and audio files.
2K output
Higher-resolution renders for final delivery.
What MiniMax H3 can do
Text to video
Describe the scene and sound.
First / last frame
Pin the start and end images.
Multimodal references
Guide people, products, motion and sound with references.
4–15-second clips
Pick a length from 4 to 15 seconds, with sound generated in the same pass.
768p and 2K output
Choose 768p and 2K in 6 aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16.
Reference inputs
Besides a text prompt you can add a first frame and an optional last frame and up to 15 reference files.
Use cases
Starting points you can copy into the generator above.
| Use case | Good for | Example prompt |
|---|---|---|
| Commercials | Multi-shot product spots. | Shot 1: the bottle from the reference on a kitchen counter. Shot 2: a hand pours it into a glass. Shot 3: a family smiles at breakfast; upbeat acoustic music |
| Music clips | Sound-driven scenes in stereo. | A street drummer plays on upturned buckets in a busy square, crowd cheering, stereo sound panning |
| Character videos | Keep a face across shots. | The woman from the reference images walks through an autumn park and sits on a bench, leaves falling |
| Cinematic 21:9 | Wide-screen scenes. | 21:9: a spaceship lifts off from a desert at dawn, sand swirling, deep rumble |
MiniMax H3 in 3 steps
- 1
Describe the shot or add a frame
Write what happens, how the camera moves and how it should sound. Add a start image or references to lock the look.
- 2
Pick length, resolution and ratio
Set duration, resolution and aspect ratio. The credit cost is shown before you submit.
- 3
Generate and keep your results
Videos appear in the generator and are saved to My works. Anything that fails is refunded automatically.
X Posts About MiniMax H3 — Open-Weight AI Video with Native Stereo Audio
- MiniMax (official)@MiniMax_AI
Open weights. Shared progress. MiniMax H3 is moving fast. We built H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on. Recent highlights: •… pic.twitter.com/4ErQ9AgAIX
View on X - Tech Buzz China@TechBuzzChina
MiniMax H3 video model opens a path around closed AI video vendors MiniMax open-sourced H3, a multimodal video model it calls "Seedance-level." It takes up to 9 images, 3 video clips, and 3 audio tracks, 12 files max, and turns them into finished-feeling spots. APPSO testers… pic.twitter.com/Vg6He6UpN8
View on X - MiniMax (official)@MiniMax_AI
Huge thanks to @ComfyUI for an incredible livestream! From reference-to-video and native audio, to multi-shot commercial creation, MiniMax H3 showcased the expanding possibilities of open-weight video models. The stream also took a deep dive into quantization, offloading,… https://t.co/u1IotCbeVy pic.twitter.com/qKk5bBkITy
View on X
YouTube Videos About MiniMax H3 — Open-Weight AI Video with Native Stereo Audio
The BEST local AI video generator is here! Minimax H3 tutorial
AI Search · YouTubeI Tested MiniMax H3 + MiniMax Design — This Changes the AI Video Workflow
Next Evolution AI · YouTubeMiniMax H3 Is INSANE | The AI Video Generator That Understands Everything
TryThisAI · YouTubeMiniMax-H3 First Look: How Good Is It?
VividMuse · YouTubeMINIMAX H3 JUST GOT EVEN BETTER!
Aitrepreneur · YouTubeI Tested MiniMax H3 on MiniMax Design | The Ultimate Multimodal AI Video Generator?
Zoetry AI · YouTube
Frequently asked questions
MiniMax released H3 with open weights in August 2026. On this site you can use it without any setup.
Up to 15 reference images, videos and audio files in reference mode, or a first and last frame in image mode.
From 24 to 146 credits per video, depending on duration, resolution. The exact cost is shown before you submit, and failed generations are refunded automatically.
768p and 2K; aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16. Clips run 4–15 seconds.
No. MiniMax H3 is developed by MiniMax; Nano Banana is an independent service that runs it through a model provider.
Ready for 2K Video with Stereo Sound?
MiniMax H3 makes 2K video with native stereo audio and up to 15 reference images.
- Clips up to 15s
- Native audio
- Failed outputs refunded