Highlights:
- Alpha release of Text-to-Speech support including generation on CUDA and MLX, and training on CUDA!
- Ability to trigger a workflow through transformerlab-client
- Fix for the stalling download error some users were getting on gated models
- Diffusion has been converted to run as a plugin like other loaders
- Upgrades to key libraries to support newest models (torch, transformers)
- API reorganization to move jobs under experiments
What's Changed
- Remove audio URL from UI after speech is generated by @mina-parham in #720
- Move Jobs Router under Experiment by @aahaanmaini in #701
- Fix Audio Player for datasets preview by @deep1401 in #729
- Fix stopping of jobs by @deep1401 in #739
- Update Old Job Endpoints under Experiment by @aahaanmaini in #740
- Fix/audio engine filtering by @mina-parham in #733
- Convert Image Diffusion to a Plugin by @Sourenm in #628
Full Changelog: v0.21.1...v0.22.0