Skip to content

v0.210.0

Latest
Latest

Choose a tag to compare

View all tags
@github-actions github-actions released this 08 Oct 08:51
v0.210.0
e836ffc

Generation

AI generation is back, now on the Diffusion Studio API. Make images, video, music, sound effects and speech from the prompt bar, which shows your credits and what a generation will cost before you start. The model menu is searchable, and video models get a duration slider. New voice model: Gemini 3.8 Flash TTS.

  • generate and job tools: agents can run any model, price it first with estimate, and poll the job until its files are saved to the library. Every model and its fields are listed in the models reference.

Changes

  • Tool names: the media_ prefix is gone. media_grab is now grab (diffusion grab), and the same goes for probe, transcribe, filmstrip, waveform and listen. Object segmentation moved from media_segment to generate sam-2.1, and the models and voices tools are replaced by the models reference.
  • Agent chat: paste files straight into the message box.
  • Captions: a shimmer shows while captions are being generated.

Full Changelog: v0.209.1...v0.210.0

Assets 7
Loading