Upload README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,7 @@ tags:
|
|
| 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 |
- If the model folder that you are upgrading already has a VAEEncoder.mlmodelc file inside, rename that file to VAEEncoder.mlmodelc.bak first, to keep it in case you want to return to it later. It is fine to leave it in the folder. It only needs to be renamed.
|
|
|
|
| 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 |
+
These VAEEncoders were built from vae-ft-mse-840000-ema-pruned.ckpt. That is the VAE that was distributed with the original Stable Duffusion 1.5 model. It is the VAE used in the vast majority of trained and merged 1.5-type models. There is an alternate VAE, kl-f8-anime.ckpt, that is sometimes used instead, in anime-focused models. I believe that the diferences in that VAE are only relevant to the VAEDecoder. These are replacement VAEEncoders, not VAEDecoders. If your model has the kl-f8-anime VAE baked in, it will still do its job through the VAEDecoder.
|
| 19 |
|
| 20 |
### INSTRUCTIONS
|
| 21 |
- If the model folder that you are upgrading already has a VAEEncoder.mlmodelc file inside, rename that file to VAEEncoder.mlmodelc.bak first, to keep it in case you want to return to it later. It is fine to leave it in the folder. It only needs to be renamed.
|