Download
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
Re-trained on Anima Base v1.0, 20 epoch, using Prodigy optimizer for the first time. It's pretty good, but the style is a bit weaker, I doubt it'll work great with distilled models.
Usage: Recommended strength between 0.8 and 1.0. At 1.0, mangled hands can occur, particularly when holding weapons.
Tested on:
RDBT Anima (CFG 2, 12 steps, Euler)
AnimaYume v0.4 (CFG 5.5, 30 steps, Euler)
animapreview_v3 (CFG 5.5, 30 steps, Euler)
Anima Turbo LoRA v0.1 with both Animayume and animapreview_v3 (CFG 1, 12 steps)
Generating text: At strength 1.0 this can be unreliable. Lower the LoRA strength until it works, or try reducing CLIP strength first as that alone is sometimes sufficient.