jrrjrr commited on
Commit
b05d955
1 Parent(s): b157861

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -5,18 +5,18 @@ tags:
5
  - stable-diffusion
6
  - image-to-image
7
  ---
8
- # These are a set of VAEEncoder.mlmodelc bundles that will enable the image2image feature with Mochi Diffusion 3.2 when using incompatible older CoreML converted models.
9
 
10
- **They are provided in a single zip file, containing five VAEEncoder.mlmodelc files, noted by their file names for use as follows:**
11
- - for split_einsim 515x515 SD-1.5 type models
12
- - for original 512x512 SD-1.5 type models
13
- - for original 512x768 SD-1.5 type models
14
- - for original 768x512 SD-1.5 type models
15
- - for original 768x768 SD-1.5 type models
16
 
17
- **They should enable image2image for ANY model trained or merged from the Stable Diffusion v1.5 base model. They will not work with models derived from Stable Diffusion v2.0 or v2.1 base models.**
18
 
19
- **INSTRUCTIONS**
20
  - 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.
21
  - 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.
22
  - 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 the copied file's name.
 
5
  - stable-diffusion
6
  - image-to-image
7
  ---
8
+ # These are a set of VAEEncoder.mlmodelc bundles that will enable the image2image feature with Mochi Diffusion 3.2 when using incompatible older CoreML converted models.<br>
9
 
10
+ ## They are provided in a single zip file, containing five VAEEncoder.mlmodelc files, noted by their file names for use as follows:
11
+ **- for split_einsim 515x515 SD-1.5 type models**<br>
12
+ **- for original 512x512 SD-1.5 type models**<br>
13
+ **- for original 512x768 SD-1.5 type models**<br>
14
+ **- for original 768x512 SD-1.5 type models**<br>
15
+ **- for original 768x768 SD-1.5 type models**
16
 
17
+ ### They should enable image2image for ANY model trained or merged from the Stable Diffusion v1.5 base model. They will not work with models derived from Stable Diffusion v2.0 or v2.1 base models.<br><br>
18
 
19
+ ### INSTRUCTIONS
20
  - 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.
21
  - 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.
22
  - 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 the copied file's name.