Updated: May 17, 2026
styleDownload
1 variant available
The 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
First lora training try on Anima, base model Anima-base-v1.0
Recommended Weight: 1.0~1.5 (usually I use 1.1 or 1.2)
Trigger words: @sanuki
PS: No prodigy, no Adafactor, using AdamW8bit and guessing the learning rate is so annoying, this lora is not perfect so far, may improve later.
Check my Sanuki Style lora for illustrious-XL if you need:
Sanuki(さ抜き) Style (for Illustrious-XL) - v1.0 | Illustrious LyCORIS | Civitai