SD to Core ML v1.3a

Removed some unnecessary spaces found in the conversion commands

SD to Core ML v1.3

Added ControlNet support

SD to Core ML v1.2c

Changed ⌘. to ControlC to quit for more compatibility between terminals.

SD to Core ML v1.2b

• Indentation is now 4 spaces instead of 3
• Reduced size of section headers
• Better phrasing in paths comments
• Added tilde expansion to paths

SD to Core ML v1.2a

Fixed a typo that displayed some sentences incorrectly

SD to Core ML v1.2

Now with spinners 🥳

Oh, also:

• Added a menu option to change the model's name, which is also become the main loop
• After zipping, asks whether to delete (trash) the model and its folders

Is zipping even a word? Been saying it out loud for a while, and it stopped making sense at some point

SD to Core ML v1.1

• Added model name to displayed messages
• Better phrasing in displayed messages
• Fixed a typo in a menu option that made it unselectable
• Fixed zip being verbose by adding -q

SD to Core ML v1.0

New and improved all-in-one version, with option selection and much more 🥳
Straight to v1.0 from v0.1 because it's that much better 😎

Features

• Works with both CKPT and SafeTensors file format
• Display a log message and a system notification with status updates
• If a conversion fails, will attempt it every 30s until it's successful
• Resume your conversions at any time by entering the model name
• Automatically delete all unnecessary files once the conversion is done
• When converting to All, ask to zip folders (useful for sharing purposes)
• Super simple, just set your model name and choose an option
• Some easter eggs 👀

SD to Core ML v0.1

Multiple script to convert Stable Diffusion CKPT models to Core ML:

• convert_to_all: converts CKPT → Diffusers; Diffusers → ORIGINAL, ORIGINAL_512x768, ORIGINAL_768x512, and SPLIT_EINSUM
• convert_to_diffusers: converts CKPT → Diffusers only
• convert_to_original: converts Diffusers → ORIGINAL only
• convert_to_original_512x768: converts Diffusers → ORIGINAL_512x768 only
• convert_to_original_768x512: converts Diffusers → ORIGINAL_768x512 only
• convert_to_split-einsum: converts Diffusers → SPLIT_EINSUM only