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
Add base_model metadata (nvidia/Cosmos-Predict2-2B-Text2Image)
#177
by victor HF Staff - opened
This repo currently has no base_model set in its card metadata, so it doesn't appear in any model's tree:
base_model:
- nvidia/Cosmos-Predict2-2B-Text2Image
Setting this will surface the model in nvidia/Cosmos-Predict2-2B-Text2Image's Model Tree (under its quantizations/finetunes) and improve discoverability for people browsing from the base model.
Feel free to merge directly (or close).
@victor What is the standard practice on HF for models that are significant architecture modifications of a base model? Do they still typically set the base_model? Anima's DiT is finetuned from Cosmos2, but the different text encoder and LLM adapter module means it's not a drop-in replacement for Cosmos2. No code that runs Cosmos2 will run Anima.