fal Assets is live.
Everything you generate on fal lives in one library now: images, video, audio, 3D. Semantically searchable, and instantly reusable as input across Sandbox, Playground, and Workflows.
No re-uploading. No filename hunting. Just "the angry one" or "the sunset clip" and you're back in flow.
Happy hour at #CVPR2026 tomorrow ๐ธ
Come meet @a16z infra + a dozen of the best generative media & computer vision teams in one place.
I can promise great food, drinks, and company!
RSVP๐
Sonilo v1.1 is live on fal.
A professionally licensed video-to-music AI model from @Sonilo_music that generates original soundtracks directly from your footage in seconds.
Upload a video, get music that matches its pacing, emotion, and story instantly.
Krea 2 Turbo drops on fal!
Deep aesthetic understanding for concept art, fashion and editorial
Compatible with style refs for locked-in visual direction
Turbo speed for rapid iteration without losing quality
Open speech models for real-time voice agents.
@NVIDIAAI Nemotron 3.5 ASR is now available on fal.
An open streaming speech recognition model supporting 40 language-locale combinations with ultra-low latency, native punctuation, and capitalization.
Built for voice agents, call centers, meeting transcription, live captions, and in-car assistants.
Some jaw-dropping demos at our 3D GenMedia Meetup last night.
Builders from across the 3D and generative media ecosystem shared a glimpse into where AI-generated materials, virtual worlds, animation, and creative tooling are headed.
Huge thanks to everyone who demoed their work, and to @KindredVentures for hosting us.
Thread of highlights โ
@mattworkman Sick demo from @BenjaminPain showing his new model, PATINA, a first-of-its-kind PBR texture generation model, inside Blender to rapidly render.
๐จ MAI-Image-2.5 is now live on fal!
๐ธ Photorealistic images with natural lighting and accurate skin tones
Refined text rendering for branding, packaging, and commercial design
Text-to-image and image editing with precise, design-ready control
TripoSplat is now live on fal!
Single image to high-quality 3D Gaussians in under 5 seconds
Learned density control for sharper detail with fewer particles
Controllable Gaussian budgets for hero assets, backgrounds and LOD
Introducing Ideogram 4.0: the best open image model in the world.
Think it. Make it. Own it.
Download the weights, fine-tune on your own data, and run it on your hardware. Live on every Ideogram plan and the API today.