Add variants description to model card (#2)

README.md

@@ -16,7 +16,21 @@ The model is trained from scratch 550k steps at resolution `256x256` on a subset
 
 ![image](https://github.com/Stability-AI/stablediffusion/blob/main/assets/stable-samples/txt2img/merged-0003.png?raw=true)
 
-These weights here have been converted to Core ML for use on Apple Silicon hardware. Please, refer to https://huggingface.co/blog/diffusers-coreml for details.
+These weights here have been converted to Core ML for use on Apple Silicon hardware.
+
+There are 4 variants of the Core ML weights:
+
+```
+coreml-stable-diffusion-2-base
+├── original
+│   ├── compiled              # Swift inference, "original" attention
+│   └── packages              # Python inference, "original" attention
+└── split_einsum
+    ├── compiled              # Swift inference, "split_einsum" attention
+    └── packages              # Python inference, "split_einsum" attention
+```
+
+Please, refer to https://huggingface.co/blog/diffusers-coreml for details.
 
 - Use it with 🧨 [`diffusers`](https://huggingface.co/stabilityai/stable-diffusion-2-base#examples)
 - Use it with the [`stablediffusion`](https://github.com/Stability-AI/stablediffusion) repository: download the `512-base-ema.ckpt` [here](https://huggingface.co/stabilityai/stable-diffusion-2-base/resolve/main/512-base-ema.ckpt).