# FAQ **Q: Which type of model should I choose for downloading?** A: Opt for the split-einsum model if you have lower performance requirements. The original model type demands better device specifications (e.g., M1 Max 32GB). **Q: How can I avoid application crashes?** A: 1) Enable the "Reduce Memory Usage" option, which optimizes memory consumption but might increase drawing time; 2) Set the iteration steps to a smaller range, e.g., 10; 3) Close other software and services to increase available system memory. **Q: Why is the model download speed so slow?** A: Currently, model files are hosted on Huggingface servers. Slow download speeds might occur in certain regions; users might need to use proxies to download from Huggingface. **Q: Why is the drawing process so slow?** A: Running AI drawing locally on mobile devices demands significant resources. The initial model run incurs extra time, but drawing speed improves after loading. --- # Agent Instructions: 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://doc-en.joyfusion.app/faq.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.