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
License concerns
I've heard the license is fairly restrictive on this model, and I've skimmed through it myself a bit, me personally never wanted to use it in a way that would be prohibited anyway so personally it doesn't matter directly. However, I am worried this will become another SD3 situation when it comes to platforms like CivitAI and they will avoid it like the plague, and completely kill off hype for this model and make finding LoRAs harder. Are these concerns founded? I really want to be able to browse easily for finetunes and LoRAs of this model, and I'm not sure if the license is to blame or CivitAI being slow
Regarding the license, the model is based on Nvidia's Cosmos 2b, which has a non commercial license which Anima can't change, and regarding the loras, Official training code isn't out yet
correction: Support just released*
https://huggingface.co/circlestone-labs/Anima/discussions/37
I wrote a post explaining the license in detail. It is less restrictive than the Flux license. I don't have any right to take down derivatives such as loras, as long as they aren't blatantly breaking the law.