Seedance 2.5: Seedance 2.5 is now available for image generation, bringing improved quality and consistency to the Seedance model line.

Seedream 5.0 Pro Layerize: A Layer-optimised variant of Seedream 5.0 Pro, tuned for style consistency across batches.

FLUX.3 Video Extend and Grok Imagine Video Extend: You can now extend the duration of a generated video using FLUX.3 Extend directly from the video lightbox, with Grok Imagine Video Extend as a second extension option — giving you two distinct paths for lengthening clips without re-generating from scratch.

Sonilo 1.1 — music and sound effects: Six Sonilo 1.1 models are now available covering music and sound effects generation, with support for text and video inputs and output as audio-only or muxed video with audio.

Meta SAM 3.1 and SAM 3D: Meta SAM 3.1 is now available for image and video segmentation. Three SAM 3D models are also live — SAM 3D Objects, SAM 3D Body, and SAM 3D Align — enabling image-to-3D generation with GLB output across object, character body, and alignment workflows.

Hi3D family: The Hi3D model family is now available for image-to-3D generation.

Hyper3D Rodin: Hyper3D Rodin expands with three new options: Rodin Bang for mesh segmentation, and Rodin Gen-2 and Gen-2.5 for text-to-3D and image-to-3D with GLB output and configurable mesh modes and materials.

Draw-video: You can now sketch motion arrows directly onto a still image to generate an on-device reference clip, which feeds into video generation slots as a motion reference — giving you direct control over how elements in a scene should move.

Hide assets instead of delete: Assets on your board can now be hidden rather than permanently deleted, so you can keep your workspace tidy without losing work you might want to revisit.

Thinking and web search on Gemini and Luma models: Thinking level controls and web search are now available when using Gemini and Luma models in the app, giving you more control over reasoning depth and the ability to ground generations in current information.

@Reference chips now support video and audio: When referencing assets in the composer using @mentions, video and audio files are now supported alongside images — so any asset type in your library can be brought into a generation as a reference.

Drag and drop into composer: You can now drag assets directly into the composer input rather than uploading or selecting from a picker, making it faster to bring existing assets into a new generation.

Home quick actions: Edit tools are now accessible directly under the home composer, so common actions are one step closer without navigating into a specific session or asset view.

Gemini restored in Inpaint and Reframe: Gemini models are now available again as options inside Inpaint and Reframe workflows after being incorrectly excluded in a recent update.

Clearer inference error detail: Error messages returned from failed inference runs now include more specific detail about what went wrong, making it easier to diagnose and retry without guesswork.

Large workspace member search: Searching for members in workspaces with large team sizes now works correctly, resolving a performance issue that caused the search to return incomplete or no results.

Rodin Gen-2 and Gen-2.5 style fix: Resolved a 500 error caused by a style-path unpacking issue in Hyper3D Rodin Gen-2 and Gen-2.5 generation requests.