This version adds a variety of user requested image generation models compiled for mobile use:
 |  |
 |  |
Lorebook supports importing webpages from links
In this update, Lorebook supports importing a link. Layla will read the webpage behind the link, strip the HTML, and convert the content into a Lorebook so you can chat with it.
Kokoro TTS model
v5.2.0 also adds the new Kokoro text-to-speech model. This is a lightweight model that was released in the last few weeks, with amazing quality voices (even including an ASMR voice!)
Full Changelog:
New features:
added SD Dreamshaper, Chilloutmix NPU model
added SD Hassaku CPU model
added iniVerse Mix Layla Cloud model
added Cohere API support
added support for importing webpages as Lorebooks
added support for Kokoro TTS model
Improvements:
optimised Character Selection page: added sorting options, optimised loading a large number of characters
Bug fixes:
fixed bug where {{instruction}} tags were being force injected for some characters
Comments