# Input requirements One of the challenges of training an AI model to generate avatars is the need for high-quality input data. In many cases, this requires input images that are clear and free from noise or artifacts, and that only contain the face of the subject without any accessories or obstructions. However, by being able to train on input data that is less strict and includes accessories, Cavatar is able to work with a wider range of input images and produce more varied and interesting avatars. This can be particularly useful in applications where users may want to create avatars that include accessories or other elements that are important to them. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://cavatar.gitbook.io/cavatar.io/technology/how-it-work/input-requirements.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.