AI Video

On July 23, Black Forest Labs announced FLUX 3. The headline capability is easy to understand: one generation can produce up to 20 seconds of video with native audio. It was quickly described in some corners as an open-source answer to Veo and Sora. I think that claim is premature. At launch, FLUX 3 is still in Early Access. Black Forest Labs has not published API pricing and has not promised when, or whether, FLUX 3 video weights will be released. The company has a real history of open-weight releases, but a company having open-weight products does not make every new model open source. ...

I’m more and more convinced of one thing: AI video is heating up again not because models suddenly learned how to make films, but because the input layer changed. For a while, everyone treated prompt writing like a contest. You had to know shot language, pacing, style cues, and how to avoid broken hands, broken faces, and broken subtitles. That works for power users. For everyone else, it gets old fast. People are not here to take a prompt exam. They are here to ship content. ...

I increasingly think the most important race in AI video is not who understands prompts better. That may sound odd. For the past two years, AI video has been almost inseparable from prompting: how to describe camera movement, how to specify style, how to keep characters consistent, how to avoid broken hands, fake text, and weird cuts. People who write better prompts do get better results. But that is also the problem. ...