Update README.md

README.md

@@ -1,3 +1,28 @@
 ---
 license: creativeml-openrail-m
+tags:
+- coreml
+- stable-diffusion
+- image-to-image
 ---
+# These are a set of VAEEncoder.mlmodelc bundles that will enable the image2image feature with Mochi Diffusion 3.2 when using incompatible older CoreML cpnverted models.
+
+**They are provided in a single zip file, containing five replacement VAEEncoder.mlmodelc files, noted by their file names for use as follows:**
+- for split_einsim 515x515 SD-1.5 type models
+- for original 512x512 SD-1.5 type models
+- for original 512x768 SD-1.5 type models
+- for original 768x512 SD-1.5 type models
+- for original 768x768 SD-1.5 type models
+
+**They should enable image2image for ANY model trained or merged from the Setable Diffusion v1.5 base model.  They will not work with models derived from Stable Diffusion v2.0 or v2.1 base models.**
+
+**INSTRUCTIONS**
+- Rename the existion VAEEncoder.mlmodelc inside the model folder you wish to upgrade to VAEEncoder.mlmodelc.noi2i
+- Copy the appropriate new VAEEncoder.mlmodelc to the model folder of the model you are upgrading.  The new VAEEncoder.mlmodelc file needs to match the original model in size and compute unit type.
+- Examples:  If the model is an original 512x768 model, copy the file named NEW-ORIG-512x768-VAEEncoder.mlmodelc.  If the model is a split_einsum 512x512 model, copy the file named NEW-SPLIT-512x512-VAEEncoder.mlmodelc.
+- After copying the appropriate VAE file, you must rename it to VAEEncoder.mlmodelc.  That means removing the NEW-ORIG-512x768-, NEW-SPLIT-512x512-, etc. from thr copied file name.
+- The upgraded model should now work with both image2image and text2image.
+- IMPORTANT:  remeber that in image2image, your STARTING IMAGE must always be the same size as yout model.  A 512x512 model will only work with a 512x512 starting image, a 768x512 model will only work with a 786x512 starting image., etc
+- Both the model and the starting image sizes are listed as WIDTH x HEIGHT.  512x768 is a "portrait" orientation.  768x512 is a "landscape" oriemtation.
+- In the even that the updated VAEEncoder.mlmodelc does not work for you, delete it and revert to your backed-up file by removing the .noi2i from the back-up's name.
+- Please report any issues you encounter so I try resolve them.