Anima2-GGUF / README.md
JusteLeo's picture
Update README.md
6e5b670 verified
|
Raw
History Blame
1.68 kB
metadata
license: other
license_name: circlestone-labs-non-commercial-license
license_link: https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.txt
tags:
  - stable-diffusion.cpp
  - gguf
  - anima
  - image-generation
  - quantized
base_model:
  - circlestone-labs/Anima
base_model_relation: quantized

ANIMA2-GGUF

These are GGUF quantized versions of the Anima 2 (Preview 2) model, explicitly compiled and quantized using the stable-diffusion.cpp library. These files are optimized for local inference on low-RAM devices while maintaining high generation quality.

How to Use

Ensure you are using the latest version of stable-diffusion.cpp (Anima support is recently integrated, so a fresh build or latest release is highly recommended).

./bin/sd-cli \
    --diffusion-model /path/to/anima-preview2_q4_k.gguf \
    --llm /path/to/qwen_3_06b_base.safetensors \
    --vae /path/to/qwen_image_vae.safetensors \
    --vae-tiling \
    --steps 30 \
    --cfg-scale 4 \
    -W 1024 -H 1024 \
    -p "a cute blue cat in a park" \
    -o output.png

(Note: The --vae-tiling flag is recommended to prevent out-of-memory errors during the image decoding phase).

Acknowledgments and Credits

  • Original Model: circlestone-labs.
  • Engine: Compiled and quantized using the stable-diffusion.cpp project for making local AI accessible.
  • Implementation: Special thanks to GitHub contributor @rmatif for his work on the implementation of Anima support.
  • License: These files are subject to the circlestone-labs-non-commercial-license.