Fal made its H3 Max reference-to-video model generally available on September 6, claiming real-time generation with up to four references and speeds up to twice as fast as its preview. The API support…
Fal launched H3 Max Director on September 3, an API that turns short generated clips into a live, steerable WebRTC video-and-audio session, supporting 24 fps output and memory for up to 50 earlier pro…
Fal, the San Francisco-based generative media platform co-founded by Burkay Gur and Gorkem Yurtseven, released H3 Max on September 1, a post-trained video model based on MiniMax's open-weights H3 that…
MiniMax founder Yan Junjie is promoting a developer livestream on fal about building with the H3 video model, featuring speakers Lovis Odin, Ethan Wei, and Victor Su-Ortiz, though no date or registrat…
Fal added Bria AI's Product Dimensions API to its model gallery on July 16, giving developers a hosted endpoint that turns a product photo and supplied measurements into a marketplace-ready image with…
Fal has added ByteDance's Seed Audio 1.0 to its hosted model gallery and API, enabling developers to generate audio from text, reference audio, or images through a single endpoint. The move positions …