AI Video Model Review
Other Other 2026-08-26
Footage © @ArtificialAnlys · View original post
The clip was published publicly by its creator and is linked here directly; rights holders may request removal.
Full prompt
MiniMax H3 Max, a post-trained version of MiniMax H3 developed by fal, debuts at #1 in Image to Video and #3 in Text to Video on the Artificial Analysis Video Leaderboards with Audio, ahead of the base MiniMax H3 on both MiniMax H3 Max is built and served by fal, and post-trained from MiniMax H3. fal describes it as being tuned for stronger prompt adherence and better aesthetics, co-optimized with their custom inference stack for higher throughput. It generates 5 to 15 second clips with native audio at up to 768p. In the Artificial Analysis Video Arena, H3 Max ranks #1 in Image to Video with Audio, narrowly ahead of ByteDance's Dreamina Seedance 2.0 720p. It ranks #3 in Text to Video with Audio, on a board where the top three models sit within 6 points of each other. fal prices MiniMax H3 Max at $0.04 per second of 768p video ($2.40 per minute). The base MiniMax H3 endpoint on fal is $0.06 per second at the same resolution. fal has stated its intent to release the weights for MiniMax H3 Max. If it does, H3 Max would become the highest ranked open weights model on both boards, ahead of MiniMax H3, which leads on open weights today. Congratulations to @fal on the release! See below for comparisons between MiniMax H3 Max and other leading models in the Artificial Analysis Video Arena 🧵 ### 作者补充 [补充1] MiniMax H3 Max, a post-trained version of MiniMax H3 developed by fal, debuts at #1 in Image to Video and #3 in Text to Video on the Artificial Analysis Video Leaderboards with Audio, ahead of the base MiniMax H3 on both MiniMax H3 Max is built and served by fal, and post-trained from MiniMax H3. fal describes it as being tuned for stronger prompt adherence and better aesthetics, co-optimized with their custom inference stack for higher throughput. It generates 5 to 15 second clips with native audio at up to 768p. In the Artificial Analysis Video Arena, H3 Max ranks #1 in Image to Video with Audio, narrowly ahead of ByteDance's Dreamina Seedance 2.0 720p. It ranks #3 in Text to Video with Audio, on a board where the top three models sit within 6 points of each other. fal prices MiniMax H3 Max at $0.04 per second of 768p video ($2.40 per minute). The base MiniMax H3 endpoint on fal is $0.06 per second at the same resolution. fal has stated its intent to release the weights for MiniMax H3 Max. If it does, H3 Max would become the highest ranked open weights model on both boards, ahead of MiniMax H3, which leads on open weights today. Congratulations to @fal on the release! See below for comparisons between MiniMax H3 Max and other leading models in the Artificial Analysis Video Arena 🧵 [补充2] Text to Video (With Audio) Prompt [1/2]: A clear glass of water sits on a table in front of a piece of paper with blue text. The camera moves side to side; the text seen through the water should be magnified and distorted, while the text beside the glass remains normal. https://t.co/G73ghcDUsx [补充3] Text to Video (With Audio) Prompt [2/2]: A hand catching a ball, fingers spreading on impact, wrist absorbing shock, then grip tightening. All in slow motion. Audio: Ball smack. https://t.co/kJcQQZUvHL [补充4] Check out MiniMax H3 Max for yourself on the Artificial Analysis Video Leaderboards: Text to Video: https://t.co/4Z2WdlyXtq Image to Video: https://t.co/QJznzx1mKv Or vote in the Video Arena: https://t.co/ksERo0WDcM
Details
| Target model | MiniMax H3 |
|---|---|
| Use case | Other |
| Style | Other |
| Media | Video |
| Duration | — |
| Aspect ratio | 270:247 |
| Likes | 844 |
| Published | 2026-08-26 |
Attribution
Author: @ArtificialAnlys · View original post
Prompts remain the copyright of their authors. We index and quote them with attribution plus a link to the original post; rights holders may request removal.
Run this prompt through the API
Copy the prompt above into a MiniMax H3 (Hailuo) text-to-video call to reproduce the shot. When adapting it, swap subject, setting and camera move one clause at a time. Access and licensing details are on About.