Download
1 variant available
3630 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2810 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2650 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(67)
Apr 23, 2026
Rumi & Sakie's Anima model version. Anima is still in the exploratory stage, and many aspects are not yet fully refined — please bear with us. For prompts, you can use natural language or write with regular tags. If anything is unclear, you can refer to the example images for guidance. Please note that this version suffers from overfitting and may produce blurry images. I will work on releasing an additional version later to address these issues.
Show more


1.9K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
18.4K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
AnimaThe Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Built on NVIDIA Cosmos
With the Anima version, you have greater freedom to write prompts in natural language. It is highly recommended to use it together with the Anima Highres and Anima Turbo LoRAs for noticeably better image quality. I'll be working on providing a higher-fidelity version later. As for LoRA weight, please decide based on your own needs — if you're aiming for an illustrative look, a lower LoRA weight generally yields better results. Hope you enjoy using it!
using the two-character lora model trained by Noobai, there is a high possibility of bad pictures in two-person interaction, please try more.
cgf:5-5.5
step:20-25
weight: 0.6-0.8

