New video models — Gemini Omni Flash: You can now generate video using three new Gemini Omni Flash models — text-to-video, reference-to-video (up to 5 reference images), and prompt-driven video editing — all at 720p with native audio and support for both 16:9 and 9:16 formats, so you have a fast, versatile video generation option directly in your pipeline.

New image models — Recraft V4.1 and Reve 2.0: Four new Recraft models are now available — Recraft V4.1, V4.1 Pro, V4.1 Vector, and V4.1 Pro Vector — covering both raster and SVG text-to-image generation. Reve 2.0 and Reve 2.0 Remix are also live, adding a new direct-API image provider with support for text-to-image, editing, and 1–6 image remixing in a single run.

Public workflow sharing: You can now share any workflow publicly with a single link. Recipients get a read-only view and can make their own copy to edit, so distributing and collaborating on workflows no longer requires manual exporting or workspace access.

Train Krea 2 Turbo: Krea 2 Turbo is now available for LoRA model training, so you can fine-tune it on your own assets and apply a consistent style across generations.

The work we mentioned last time is still underway — and getting closer. We're genuinely proud of what's taking shape and want to make sure it's right before we share it. If you've been using Layer regularly, we think you're going to feel the difference immediately.

More soon!