Layla v6.5.0 has been published!

This version of Layla brings a new redesigned character selection screen. This will give you a quick overview of your character, including how many chats you've had with them, how many memories they have, and more!

This screen also gives you options to easily configure aspects such as favouriting the character, editing the character, or continuing or starting a new chat.

Advanced Settings Preset

This version also allows you to save your own advanced settings, for things such as temperature, xtc probability, etc.

Lots of models require their own sampler parameters. For example, some fine-tuned model creators recommend specific settings of temperature and top p to get the most out of the model. You can now attach these settings to your own Inference Engine, which will automatically apply them when you start a chat using those models.

You can do this by going to Settings -> Inference Settings -> scroll down to save custom Inference Engine.

Full Changelog

New features:

• redesigned character selection page to give you detailed information of your character before starting the chat

• added ability to save custom sampler settings in the Advanced Settings screen

• added ability to attach saved sampler presets as part of your custom Inference Engine

Improvements

• supports sending images to OpenAI compatible API inference settings

Bug fixes:

• fixed a bug where some app data was not deleted when removing a mini-app from Layla

• fixed a bug where LTM sometimes crashes when handling very very long messages

• fixed a bug where images generated during chat were not being backed-up

• fixed a bug where tags from TavernPNG were not being imported

• fixed a bug where backup cannot copy references with spaces or special characters in their name

• fixed a bug where automatically converting JPGs when saving as TavernPNG was giving an error

• fixed a bug where personas were not being saved as part of your Inference Engine

• fixed a bug where upscaling anime images caused a crash

• fixed a bug where chat with LTM crashes on the latest Snapdragon Gen5 CPU