Instructions to use AnticPan/Anima-Role-Ref-KV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AnticPan/Anima-Role-Ref-KV with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("circlestone-labs/Anima", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("AnticPan/Anima-Role-Ref-KV") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Commit History
3 days ago
-
Explain reference KV cache in both model cards
Verified signature259a0dc -
Clean inference package and unify Anima Role Ref KV naming
Verified signatureRemove unused training and experimental code, replace the legacy charref package with anima_role_ref_kv, and update imports and notices. Validated both public weight formats and the real ComfyUI workflow on GPU; generated images match the previous release exactly.b2e97d8 -
Restore previous showcase
Verified signatureeb3e769 -
Refresh character-reference showcase
Verified signature4f1e5fb -
Release Anima Role Ref KV v1.0
Verified signature6b7dcac -
initial commit
Verified signature26ff232