It's very clear that the @fal team deeply understands what it takes to get AI into the mainstream and is in the center activating the AI + media inflection point (not to mention h3max/fal.live from a few weeks back) @burkaygur @emir_lise please take all of my money

Introducing fal Recast, an easy way to change any character in one click. Upload an existing video + a reference photo of your new character. fal Recast changes who’s on screen while preserving the original motion, camera movements, cuts, and audio. Create character variations, adapt campaigns for different audiences, all without another shoot. Powered by H3 Max, the #1# model for overall quality, prompt understanding, and aesthetics against leading video models.

fal CTO @gorkem says generative media just hit "token market fit," with professionals now spending entire workdays generating video with AI: "Since then, it really reached professional level, and we call it token market fit. Generative media has reached token market fit." "Can a single person productively spend a lot of tokens doing their work? Only coding agents have this in the AI market. No other AI sub-industry can spend this many tokens as video generation or coding agents." "People are now sitting in front of a computer at work and generating video all day long. They are willing to spend all these tokens doing their work, and this is the biggest change in generative media in the last year." @fal

Excited to announce our work "Attention Drift" has been accepted to NeurIPS 2026 🎉 I'm so happy to see our method's widespread adoptation. Now supported by all major inference engines, vLLM, Tokenspeed, SGLang and TRT-LLM. Also community trained speculative decoding models for Minimax M3 (@inferact and @AMD) and Kimi K2.6-K3 trained (@lightseekorg) being served in production as EAGLE 3.1 Shout out to all the great team mebers @themishtimoi @yigitcancomlek @kaan_oktay @hongyangzh and Stephen Xia. And special thanks to @fal for helping for making this research possible 🙂

the inference platforms are doing hardcore work, post-training open weight models to solve customer problems: @FireworksAI_HQ ember-1 @fal H3 max more to come;) makes total sense considering their position in the ecosystem, technical expertise, and economies of scale

The tote bags at our conference received so much love! We worked so hard on this mini-capsule for GenMedia Conference so thank you all for the kind words. 😵😭 Nearly every element was made and produced from scratch. - shell fabric: custom dyed nylon fabric in light sage - cord: custom developed cord 8mm cord - inside snap - metal d rings - fal logo silver carabiners - heat transfer logo - double patch pockets - care labels Some say they can be turned inside out. Made at fal design lab / @HyunjungLee_ with so much attention to detail down to the care label designs / thank you to our production partners!

A lot of late nights spent working on the opener film for GMC 😳 @MichelleJWu gave me such an amazing script and foundation to work off of, and the beautiful score as the cherry on top by incredible sound designer Yuta Endo! excited to see what more cool films we’ll get to make 🦋

🎨🖌️ Massive turnout for the @fal GenMedia Conference, and gorgeous venue @SHACK15sf! @TaikaWaititi + Sean Bailey from @DisneyStudios, in addition to folks from @krea_ai, @bfl_ai, @SpaceXAI, and more. Big theme is "make great things, and make sure they're the highest quality".

Packed house at the @fal GenMedia Conference! Incredible group of founders, studio heads, and creatives who are here to talk about real use cases of AI in media. Also some awesome hands-on demos, like a generative photo booth 👀

Enterprise spend on @fal more than 4x’d over the last six months. AI-native products are still the majority of usage (and growing). But there’s a new set of companies with no prior stake in generation building the kind of layered workflows you'd expect from a specialist studio: chaining models, switching modalities inside a single job, training adapters for narrow tasks. Generative media has moved from something companies experimented with to something they build on. Compute has been the binding constraint across generative media since April, by fal's own account, and their answer was post-training MiniMax's H3 to roughly 35x the throughput of the base model at matching or better quality. Tons more interesting insights into where the gen media industry is headed in the State of Generative Media Report Vol. 2. Congrats @burkaygur, @gorkem @isidentical & team.

This year we chose to make Volume 2 a work of editorial and visual art, mirroring the artistry that’s found in Gen media. The rhetoric out there is: AI replaces humans Slop Creativity is dead I wanted this year’s piece to be a resounding “to create is to be human” So we did exactly that.

can't believe we live in a time where I can make all of my intrusive design thoughts a reality. grateful for the whole team at fal who let me go crazy with the report 🙇‍♀️ excited for y’all to see the print companion piece by @clair_dlne very soon