Loading activity…
the generative media cloud. hiring https://fal.ai/careers. for support/discounts, e-mail us at support@fal.ai.
Sequoia led the earlier Series E, Bessemer led Series F, and Nvidia invested again.
Ideogram says the window edits a selected area at its original resolution while leaving pixels outside it unchanged.
Ideogram says Vector 1.0 makes editable SVGs from prompts or images, with access in Ideogram and via API at launch.
Black Forest Labs says fal adapted FLUX 3 into FLUX 3 Max, which can generate 10-second videos in 12 seconds.
Fal says the model, developed with @bfl_ai, generates a 10-second 720/768p video in about 12 seconds.
Fal says users can build characters, explore environments and direct scenes as worlds respond to their actions.
BFL says it runs on a single consumer GPU and offers native 4K generation, bounding boxes and pixel-perfect editing.
fal says users can browse generated images and videos in conversations and access their Media Library from ChatGPT.
fal says the model generates images significantly faster than Nano Banana 2 and improves mask-based editing and subject consistency.
Fal says users can upload a video and reference photo to change who appears on screen while preserving motion, cuts and audio.
The bfl_ai account also highlights text-to-image and image-to-image creation, with generation at up to 4K.
Ideogram says the model reduces pixel, color and texture changes across successive edits and preserves the edges of edited high-resolution crops.
Fal says the new endpoint lets users guide a scene with a prompt, reference images or reference videos, then insert it into existing footage.
fal says the September 24 fireside chat in San Francisco will explore how studios are adopting generative tools and what investors are watching as filmmaking evolves.
SpaceXAI pitches Grok Voice in fal as a way to build intelligent, low-latency agents that resolve customer issues.
Creatify Labs says Boreal costs one cent per second. fal says it supports videos up to 20 seconds long at up to 2K resolution, with synchronized speech, music and sound effects.
fal says the model turns a single viewpoint into a navigable 3D scene in less than three seconds and is fast enough for real-time camera control.
Official post details early preview speeds on the platform.
Chat messages direct scenes on the endless AI video channel built by Pieter Levels.
A developer linked Minimax H3 Max to Twitch for continuous live generation from chat prompts.
