China's MiniMax H3 is the first open model to top an AI video ranking
Quick Answer
MiniMax's H3 model becomes the first open AI video model to top a ranking, achieving first in Video Editing, second in Text-to-Video, and third in Image-to-Video.
Quick Take
With 33 billion parameters, it generates clips of 4-15 seconds, but commercial use is restricted to companies earning under $20 million.
Key Points
- H3 processes text, images, video, and audio together for multimedia output.
- Users can fine-tune the model with custom footage and styles.
- Commercial use is limited to companies with revenues under $20 million.
- H3's local processing in ComfyUI is capped at 768p resolution.
- ByteDance launched its closed Seedance 2.5 on the same day.
📖 Reader Mode
~1 min readMiniMax releases H3 video model weights, putting an open model at the top of a video ranking for the first time. Artificial Analysis ranks H3 first in Video Editing, second in Text-to-Video, and third in Image-to-Video. The 33-billion-parameter model processes text, images, video, and audio together, generating four- to 15-second clips with stereo sound. According to the model card, a single prompt can include up to nine reference images, three video clips, and three audio clips.
Video by MiniMax H3
Two pieces remain closed, though. The 2K resolution module and H3-Context-IR, which translates prompts and reference material into a structured intermediate format, aren't included. Running H3 locally in ComfyUI tops out at 768p, and users will need to handle context prep themselves using MiniMax's published prompting guides. The open weights do allow fine-tuning on custom footage, characters, or a specific visual style. One catch on the license side: commercial use is only permitted for companies making under $20 million in revenue.
ByteDance released its closed Seedance 2.5 the same day, which generates 30-second clips with built-in audio.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
