Added support for the new persona model in the model_name field in /image/v1/generate_gallery_image endpoint enabling image generation with significantly improved consistency in appearance and style relative to the provided reference image.
Removed the example_messages field from user_profile and updated name to be optional.
Added example_messages field to bot_profile body parameter in the https://api.exh.ai/chatbot/v3/response endpoint. This optional list parameter enables specifying example messages to guide the model in generating responses that capture the character's personality and style.
Our Image Generation API now includes a new body_type parameter, giving you better control over the avatar’s body shape in generated images. Body type options are: 'skinny', 'lean', 'muscular', 'curvy', 'heavyset'.
Our Multimodal Dialog API and Image Generation API now support selecting different generation models.
Our Multimodal Dialog API now supports selecting different LLMs to enhance your chat experience.
Our Multimodal Dialog API now supports descriptions up to 8000 characters and appearances up to 2000 characters, offering greater flexibility for detailed content.
The chatbot is now able to recognize and reference previous image content in conversations. This allows for more meaningful and contextual discussions around generated images.
Added enable_memory flag to chat_settings body parameter of https://api.exh.ai/chatbot/v3/response endpoint. This flag determines whether the long-term memory feature is used.
Added style param to https://api.exh.ai/image/v1/generate_gallery_image endpoint to generate images only in realistic or anime styles!
If nothing is passed - style is automatically predicted based on your identity image visual style.
