gguf-anima

Anima Turbo v1.1 diffusion weights in GGUF format for stable-diffusion.cpp, mirrored byte-identical from vanes430/Anima-Turbo-V1.1-GGUF for JoyFusion's on-device (Android) inference.

File	Quant	Size	SHA-256
anima-turbo-v1.1-Q4_0.gguf	Q4_0	1,235,394,688	8e57a293c36788ea646460108e6f9c43d80e608f82f24fe1adf110dd2114c712
anima-turbo-v1.1-Q8_0.gguf	Q8_0	2,239,471,744	74d6c9251f34bc4152fda460dd7befaa9cec79946c270a378fee3d33048153bd

Shared components live in JoyFusionAI/gguf-components: text encoder Qwen3-0.6B-Base.Q8_0.gguf and VAE qwen_image_vae.safetensors (Qwen-Image / Wan-2.1 16-channel VAE).

Anima is a 2B text-to-image model built on NVIDIA Cosmos-Predict2, focused on anime and illustration. Recommended for the Turbo checkpoint: 8 steps, CFG 1.0, Euler, VAE tiling on phones.

License

Anima is licensed by CircleStone Labs LLC under the CircleStone Labs Non-Commercial License v1.2 (see LICENSE.md), which permits use and distribution for non-commercial purposes only. See NOTICE for the required attribution notice. Any rights to use the model are granted directly by CircleStone Labs LLC to you under that license.