> For the complete documentation index, see [llms.txt](https://waodao.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://waodao.gitbook.io/docs/development/ai-generator.md). # AI generator WAODAO does not depend on a single AI image generator. At the beginning of the project, we used tools such as Starryai and Midjourney. Since then, the ArtChain has also included outputs created with DALL-E, Google Gemini / Nano Banana, Grok and other AI generation tools. This multi-model approach is intentional. WAODAO is not only creating daily artworks, but also documenting how AI image generation evolves over time. Different models have different strengths: some are better at composition, some at realism, some at symbolic scenes, some at unusual visual styles. By working with multiple tools, WAODAO can choose the most suitable model for each creative task and avoid dependence on any single platform. The ArtChain can continue even if a specific AI service changes its rules, pricing, access model or generation quality. If one tool becomes less suitable, the process can move to another model without breaking the logic of the daily archive. Human curation remains an important part of the process. AI models generate visual possibilities, but humans select, guide, combine and contextualize the final result. The daily artwork is not treated as a fully automatic output. It is the result of interaction between world events, trends, human input, AI models and curatorial decisions. Before an artwork becomes part of the ArtChain, we also consider the practical conditions of the tools being used, including output quality, publication rights, commercial usage rules and the general suitability of the result for the project. One of WAODAO’s long-term goals is to preserve a visible timeline of AI creativity. Over the years, the archive will show not only what happened in the world, but also how machines learned to visualize human culture, news, emotion and imagination more effectively. --- # 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, and the optional `goal` query parameter: ``` GET https://waodao.gitbook.io/docs/development/ai-generator.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.