Instructions to use circlestone-labs/Anima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use circlestone-labs/Anima with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,7 @@ The model is trained on Danbooru-style tags, natural language captions, and comb
|
|
| 44 |
- Recommended positive prefix: "masterpiece, best quality, score_7, safe, "
|
| 45 |
- Recommended negative: "worst quality, low quality, score_1, score_2, score_3, artist name"
|
| 46 |
- When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version.
|
|
|
|
| 47 |
|
| 48 |
## Tag order
|
| 49 |
[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]
|
|
|
|
| 44 |
- Recommended positive prefix: "masterpiece, best quality, score_7, safe, "
|
| 45 |
- Recommended negative: "worst quality, low quality, score_1, score_2, score_3, artist name"
|
| 46 |
- When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version.
|
| 47 |
+
- Prompt weighting works, but needs a weight higher than typically used for SDXL. Example: "(chibi:2)"
|
| 48 |
|
| 49 |
## Tag order
|
| 50 |
[quality/meta/year/safety tags] [1girl/1boy/1other etc] [character] [series] [artist] [general tags]
|