Generate multi-resolution model with one click

[czkoko]

This project breaks the limitation that Stable Diffusion CoreML Model only supports a single resolution.
No need for complicated model conversion, no need for duplicate and huge models to waste disk space,
Compatible with the official apple/ml-stable-diffusion project and apps using this project, such as Mochi Diffusion.

You just need to have a model that has been converted to coreml format, 512x512 or 768x768 resolution,
Drag and drop the model to the interface and press Enter...
Instantly you will have additional 512x768 and 768x512 resolution models, which only take up a few hundred KB of space.

Limit

- Only supports SD 1.5, SDXL can be added by yourself
- Only compatible with models converted using coremltools 7.0

https://github.com/apple/ml-stable-diffusion/assets/90698189/8d917ee9-a2a8-4e75-affc-9e0d509664dd

CoreML-Generator.zip https://github.com/czkoko/SD-CoreML-Generator