Instructions to use aina-tech/Anima-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use aina-tech/Anima-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("aina-tech/Anima-Lightning", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Cosmos
How to use aina-tech/Anima-Lightning with Cosmos:
# 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
- Local Apps Settings
- Draw Things
- DiffusionBee
ComfyUI compatible model (incl. int8) + extracted lora
#2
by awdqwdasdg - opened
I have uploaded ComfyUI compatible variants of the model (including int8) + an extracted lora (r64)
https://huggingface.co/awdqwdasdg/Anima-Lightning-Comfyui
Edit: It is usable, but needs some more work as I dropped some tensors in my conversion. Will need to address this, and a custom node will be required to load properly.
Edit 2: I have uploaded a WIP custom node that patches the time embed tensors separately. This way it can be used with the LoRA and be remapped to be used with Anima variants with extra layers (eg; Anima-2.9B).