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
Flux 2 VAE
Have you considered training for Flux 2 VAE usage?
Flux 2's VAE is miles better for fine details, which is important for artstyles, a quick encode>decode on any image shows how much better it is than qwen vae
Anyhow, thanks for such hard work!
Thank you
Have you considered training for Flux 2 VAE usage?
Yes, I have. It's not worth it, you're essentially retraining the entire model, and there is no way around it. It can be done, but the training cost/time would be too much, so it's better to wait till there is a better Flux 2 Vae-based model to train
a better Flux 2 Vae-based model to train
Well, MageFlow is architecturally quite speedy impressive
even if the base model itself isn't that useful
I see, thx for taking your time to answer :)