fal(@fal):Yesterday, we launched H3 Max. We post-trained MiniMax H3 for stronger prompt adherence and visual quality, while co-designing the inference stack alongside it. As we pushed speed, we continuously tested for quality, only keeping optimizations that preserved the gains from post-training. More on how we built H3 Max:

fal

@fal

the generative media cloud. hiring for support/discounts, e-mail us at support@fal.ai.

加入 May 2009

5 正在关注 67.3K 粉丝

fal@fal

2026.08.27 20:10

Yesterday, we launched H3 Max. We post-trained MiniMax H3 for stronger prompt adherence and visual quality, while co-designing the inference stack alongside it. As we pushed speed, we continuously tested for quality, only keeping optimizations that preserved the gains from post-training. More on how we built H3 Max:

显示更多

371

转发到社区

热门用户