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]Anima Role Ref KV
v1.0 Β· Reference-guided anime illustration for Anima Base v1.0
Generate new poses, outfits, expressions, and scenes from one character reference and a text prompt. No per-character training or trigger word is required.
The model encodes the reference image into a KV cache once per generation and reuses it across denoising steps to guide character appearance.
NSFW content was filtered out of the training data and was not used to train this release.
ComfyUI
Put the ComfyUI weights in
ComfyUI/models/loras/.Copy the comfyui folder to
ComfyUI/custom_nodes/anima-role-ref-kv/and restart.Install the base components from Anima:
File Folder under ComfyUI anima-base-v1.0.safetensorsmodels/diffusion_models/qwen_3_06b_base.safetensorsmodels/text_encoders/qwen_image_vae.safetensorsmodels/vae/Drag in the workflow, upload a reference, edit the prompt, and Queue.
The Anima Role Ref KV node loads the adapter itself; connect the original base model directly. An API workflow is also available.
Diffusers
Use Python 3.12. Download this repository and Anima Base v1.0 Diffusers, then run:
pip install -r requirements-diffusers.txt
python infer.py \
--base-model /path/to/Anima-Base-v1.0-Diffusers \
--reference reference.png \
--prompt "masterpiece, best quality, 1girl, solo, upper body, smile, garden" \
--seed 0 --output result.png
The entry point uses the Diffusers weights by default. Both formats contain the same adapter; reference generation requires the included node or Python runtime. Base components are downloaded separately.
Python import: from anima_role_ref_kv import AnimaRoleRefKVPipeline.
Settings
Start with 28 steps, CFG 4, BF16, and roughly 1 megapixel: 1024 Γ 1024, 832 Γ 1216, or 1216 Γ 832. Multiple aspect ratios are supported; dimensions must be divisible by 16. The workflow defaults to 832 Γ 1216.
Use a clear, unobstructed single-character reference and describe the desired pose, outfit, and scene. Details may drift with difficult references or strong prompt changes. Other base models, quantized weights, and additional adapters have not been validated.
License
An independent modified derivative of Anima, subject to the CircleStone model license; not an official CircleStone Labs product. Rights to the underlying model are granted directly by CircleStone Labs. Code licenses and attribution are in NOTICE.txt.
- Downloads last month
- -
Model tree for AnticPan/Anima-Role-Ref-KV
Base model
nvidia/Cosmos-Predict2-2B-Text2Image