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
|
@@ -50,7 +50,7 @@ The model is natively supported in ComfyUI. The above image contains a workflow;
|
|
| 50 |
The model is trained on Danbooru-style tags, natural language captions, and combinations of tags and captions.
|
| 51 |
- Use lowercase for tags, and spaces instead of underscores. Score tags are the only tags that use underscores.
|
| 52 |
- Recommended positive prefix: "masterpiece, best quality, score_7, safe, "
|
| 53 |
-
- Recommended negative: "worst quality, low quality, score_1, score_2, score_3, artist name"
|
| 54 |
- When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version.
|
| 55 |
- Prompt weighting works, but needs a weight higher than typically used for SDXL. Example: "(chibi:2)"
|
| 56 |
|
|
|
|
| 50 |
The model is trained on Danbooru-style tags, natural language captions, and combinations of tags and captions.
|
| 51 |
- Use lowercase for tags, and spaces instead of underscores. Score tags are the only tags that use underscores.
|
| 52 |
- Recommended positive prefix: "masterpiece, best quality, score_7, safe, "
|
| 53 |
+
- Recommended negative: "worst quality, low quality, score_1, score_2, score_3, artist name, blurry, jpeg artifacts, chromatic aberration"
|
| 54 |
- When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version.
|
| 55 |
- Prompt weighting works, but needs a weight higher than typically used for SDXL. Example: "(chibi:2)"
|
| 56 |
|