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
I have a question.
#1
by Nuke1229 - opened
How are the original 28 layers mapped into the new 40 after expansion? Which indices are old vs newly inserted?
Hi, you can check the expansion map via expand_manifest.json inside the files folder
Hi, you can check the expansion map via expand_manifest.json inside the files folder
I was just wondering—maybe for the next version, would you consider trying a different TE? One option that came to mind is Qwen3.5 4B. Someone managed to convert it to work with regular Anima: https://huggingface.co/lylogummy/anima2b-qwen-3.5-4b
(This might not be directly relevant to LTX 2.5, since it uses Gemma 4 as its TE, but it can still use LoRAs from LTX 2.3, which uses Gemma 3.)