MiniMax H3 Max登顶视频生成排行榜

MiniMax H3 Max，由fal开发的MiniMax H3的后训练版本，在人工智能分析视频排行榜（含音频）中首次亮相，图像转视频排名第一，文本转视频排名第三，两项均领先于基础版MiniMax H3。 MiniMax H3 Max由fal构建和服务，并从MiniMax H3进行后训练。fal描述其针对更强的提示遵循性和更好的美学进行了调优，并与他们的自定义推理栈共同优化以实现更高的吞吐量。它可生成5至15秒的片段，原生音频，最高支持768p分辨率。 在人工智能分析视频竞技场中，H3 Max在图像转视频（含音频）中排名第一，略微领先于字节跳动的Dreamina Seedance 2.0 720p。在文本转视频（含音频）中排名第三，该榜单上前三名模型之间的差距在6分以内。 fal对MiniMax H3 Max的定价为每秒钟768p视频0.04美元（每分钟2.40美元）。fal上的基础MiniMax H3端点在相同分辨率下为每秒0.06美元。 fal已表示有意发布MiniMax H3 Max的权重。如果发布，H3 Max将成为两个榜单上排名最高的开放权重模型，领先于目前在开放权重中领先的MiniMax H3。 祝贺@fal发布！ 请参阅下方MiniMax H3 Max与人工智能分析视频竞技场中其他领先模型的比较🧵 [回复] 文本转视频（含音频）提示[1/2]：一杯清水放在桌子上，前面是一张带有蓝色文字的纸。摄像机左右移动；透过水看到的文字应被放大和扭曲，而玻璃旁边的文字保持正常。 文本转视频（含音频）提示[2/2]：一只手接住球，手指在撞击时张开，手腕吸收冲击，然后握紧。全部慢动作。音频：球拍击声。 图像转视频（含音频）提示[1/2]：手在黑板上写“欢迎来到人工智能分析”。粉笔刮擦和轻轻敲击声。 图像转视频（含音频）提示[2/2]：手按下弹出键，VHS磁带弹出，并从播放器中取出。按钮点击声、机械嗡嗡声和塑料滑动声。

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 🧵