| --- |
| 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](https://github.com/leejet/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). |
|
|
| ```bash |
| ./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](https://github.com/leejet/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. |
|
|
