FAQ

Common FAQ List for Using JoyFusion.

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.