Instructions to use Gazingstars123/Anima-2.9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Gazingstars123/Anima-2.9B 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
Alternative booru datasets.
Would you at any point consider material from boorus such as sakugabooru and e621? Both sites have a lot of conceptual data and tags not found on danbooru. e621 in particular has very thorough tagging and classic public domain works.
Oh yeah, please consider them, specially sakugabooru,
adding sakuga would make "anime tv screencap" and "anime key frame" sorta stuff REALLY good
Yeah both have equal merit in different ways.
Sakugabooru lacks in methodical tagging but has a lot of production materials that could help bring character designs to a more canonical source. Meanwhile e621 tagging feels very complimentary and supplementary to danbooru.
Example of same image different tagging where e621 adds specifics not on danbooru:
Danbooru: https://danbooru.donmai.us/posts/7043006
e621: https://e621.net/posts/6317209
Also e621 tags concepts such as 2~6 fingers (or other limbs) which can be helpful for character design prompting consistently since even NL prompting can be hit or miss for those of us who don't prompt for canon characters.
Alternative to Sakugabooru however with no tagging system but less videos to wade through is: https://setteidreams.net/settei/