Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,14 @@ In particular, we have paid attention to characters in this iteration, and devel
|
|
| 22 |
|
| 23 |
Overall, model performs particularly well with textures and patterns that were previously simply impossible due to SDXL VAE. We prioritized keeping our training as standard-friendly as possible, so local community can easily train on it like on a new Base Model, which it practically is.
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
- **Developed by:** Cabal Research (Bluvoll, Anzhc)
|
| 27 |
- **Funded by:** Community
|
|
|
|
| 22 |
|
| 23 |
Overall, model performs particularly well with textures and patterns that were previously simply impossible due to SDXL VAE. We prioritized keeping our training as standard-friendly as possible, so local community can easily train on it like on a new Base Model, which it practically is.
|
| 24 |
|
| 25 |
+
We provide 4 models:
|
| 26 |
+
|
| 27 |
+
- Mugen: A base model.
|
| 28 |
+
|
| 29 |
+
- Mugen - Aesthetic: Slightly tuned on a limited dataset model for better quality output.
|
| 30 |
+
|
| 31 |
+
- Mugen - Aesthetic - Anzhc/Selph: Further tune on opinionated dataset selection.
|
| 32 |
+
|
| 33 |
|
| 34 |
- **Developed by:** Cabal Research (Bluvoll, Anzhc)
|
| 35 |
- **Funded by:** Community
|