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
16 days ago
-
Update ComfyUI NativeEngine for pure BF16 execution and sync v2.0 showcase assets
Verified signatureExecute BF16 LoRA projections, RMSNorm, and RoPE directly in BF16 in NativeEngine (~15.8% speedup on RTX 5090), and sync the curated v2.0 showcase/pair/case assets and model cards.d0986b6 -
Release Anima Role Ref KV v2.0 (BF16 v2.0 & v1.0)
Verified signaturePublish verified BF16 v2.0 (rr2.2 A @12000 EMA) and BF16 v1.0 adapters under versioned filenames, updated BF16/FP32-compatible Diffusers runtime and ComfyUI custom node, workflows, and bilingual model cards. Original FP32 v1.0 revision is preserved under the v1.0 tag.1e3e9a1
24 days ago
-
Release Anima Role Ref KV v1.0
Verified signature6b7dcac