🚨 New Model Alert: Qwen-Image from @Alibaba_Qwen is not available on @fal

Qwen-Image by @Alibaba_Qwen is now available at fal, as a scalable & ready-to-use API

🚨🚨🚨 I’ve developed a site where you can easily create video prompts just by using your own @FAL API key. And it’s completely OPEN-SOURCE! The project is open to further development. Looking forward to your contributions! With this site, you can: 🔽🔽🔽

Veo 3 Image to Video is finally here!

Veo 3 image-to-video by @GoogleDeepMind is now available at fal! Try it today:

There is no king of the hill in generative AI. Sora looked untouchable. Then Luma, Runway, and MiniMax dropped. Veo 3 launched. Two weeks later, Seedance leapfrogged it. "If you’re not the best, you’re not releasing." @burkaygur and @isidentical from @FAL break down what it’s like tracking the frontlines in real time. The leaderboard resets every week. It’s live combat.

All my AI startups are powered by @FAL so I invested in them They're one of the nicest people to work with, extremely fast inference times but also extremely fast support The founders are Turkish and now I have a special thing for 🇹🇷 Turkey and wanna visit Istanbul, hard working people that don't tolerate bullshit, I like it The business case for FAL seems real, I tried setting up my own GPU server on @LambdaAPI, it's fun and I got quite far installing Claude Code and letting it do everything But you still get stuck pretty fast, it's a lot of work to manage the layer between GPU and actually getting an AI model to output something fast while being able to scale up on demand (remember other startups with their "Queued" problems when you try run a job) So FAL has its role, it backs a lot of the AI apps you use because the founders want to focus on building useful apps, not mess around with GPU servers

A turbo version of Wan 2.2 just appeared on @fal. This version offers up to 2x faster generation speeds (<12 seconds per video) while slashing costs 3 times. A single 480p video is 5 cents, 720p one is 10 cents.

Wan 2.2 A14B 480p is now $0.04 per second on @fal

New Model Alert: OmniHuman by ByteDance is now available on @fal Generate vivid, high-quality videos using just a character image and audio. Emotions and movements closely match your audio, great for cartoons and non-human characters too!