5.3.0
New features:
- added a new animated character
- added ability to duplicate characters (including preset characters and animated characters, which will allow you to use the animation for your own characters)
- added XTC samplers in Advanced Settings
- added support for Phi-4 family models
Improvements:
- added feature to generate image prompt using your selected LLM in SD mini-app
- improved animated character lips movement; lips will start moving when sound is played instead of on LLM output
5.2.0
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
5.1.0
New features:
- Layla supports GPU inference! Supports Vulkan and OpenCL backends
- Layla supports NPU inference for Stable Diffusion!
- Layla supports reasoning models Deepseek R1 family!
Improvements:
- redesigned Lorebook UI to handle lots of documents better
- added ability to configure the language Whisper models listen in
- Q4_0 quants are now automatically converted on the fly
- redesigned chat message quick actions
- various bug fixes and improvements
5.0.4
- fixed bug where sometimes LTM says task not found
- fixed bug where sometimes messages were not being sent properly to Layla Cloud
4.18.4
- added Korean support for offline translator
- fixed bug when re-generating responses
- fixed bug with OpenAI and cloud models stopping response mid-sentence
- added ability to flag inappropriate content generated by the AI
- remove previous lorebooks when uninstalling the lorebook app