Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ tags:
|
|
| 7 |
---
|
| 8 |
|
| 9 |
Anime-focused ZeroDiffusion finetune. Intended for future training, NOT inference.<br>
|
| 10 |
-
Finetuned on 14117 image-caption pairs.
|
| 11 |
NSFW images were not filtered. <br>
|
| 12 |
[This](https://huggingface.co/mirav/newmoon/blob/main/NewMoon_clip_l.safetensors) was used as the text encoder, rather than ZeroDiffusion's own text encoder.
|
| 13 |
Trained on a single 24GB RTX 3090.
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
Anime-focused ZeroDiffusion finetune. Intended for future training, NOT inference.<br>
|
| 10 |
+
Finetuned on 14117 image-caption pairs at 768 resolution (with bucketing).
|
| 11 |
NSFW images were not filtered. <br>
|
| 12 |
[This](https://huggingface.co/mirav/newmoon/blob/main/NewMoon_clip_l.safetensors) was used as the text encoder, rather than ZeroDiffusion's own text encoder.
|
| 13 |
Trained on a single 24GB RTX 3090.
|