Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,7 @@ It is trained on several million anime images and about 800k non-anime artistic
|
|
| 21 |
- LoRAs should be trained using this version.
|
| 22 |
- Anima-Aesthetic
|
| 23 |
- Fine-tuned for better consistency and a higher quality default art style.
|
|
|
|
| 24 |
- Anima-Turbo
|
| 25 |
- Distilled version for fast generations.
|
| 26 |
- Use at CFG 1 and 8-12 steps.
|
|
|
|
| 21 |
- LoRAs should be trained using this version.
|
| 22 |
- Anima-Aesthetic
|
| 23 |
- Fine-tuned for better consistency and a higher quality default art style.
|
| 24 |
+
- v1.0b is an alternate version that is just an aesthetics full finetune, without additional style adjustment and stabilization loras merged in like 1.0. I personally think 1.0 is better.
|
| 25 |
- Anima-Turbo
|
| 26 |
- Distilled version for fast generations.
|
| 27 |
- Use at CFG 1 and 8-12 steps.
|