We're happy to announce that we are releasing our new Conversation Images feature to our highest tier supporters, the "I'm All In" tier. The training of private bot feature should get release next week.

When we consider the feature stable enough, we will expand its availability to the True Supporter group, possibly toward the end of November. Training of private bots will remain a feature only available to the highest tier.

How it works?

We've fine-tuned a custom AI model for each of the bots that are available for this new feature (over 55,000 public bots). This fine-tuning has allowed the AI to learn how to generate similar images, however because this is done on only 1 image, it might also attempt to replicate the style of the image or other details of the image.

When you request for an image to be generated within a conversation, we query a Large Language Model (LLM) with the definition of the bot and the last turn of your conversation and ask the AI to build an image generation prompt. We then query a diffusion model to generate an image using that image prompt.

Read all the details about this feature