Download
1 variant available
fp16 SafeTensor
RuiScreencaps_ani_v1-000030.safetensors
Half precision, best balance • 31.66 MB
Verified: 5 days ago
950 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
120 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
190 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(13)
Jul 31, 2026
This version was trained with full text encoder training (lr 1e-4).

1.9K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
4.3K0 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
A character LoRa for Rui from Pokemon. She appears in the NGC Pokemon Colosseum game as the living Shadow Pokemon detector of the protagonist. The first time I have trained a character model with 3d images only. Also I made three different versions to see how much text encoder training influences the outcome. One version I trained with my default settings (te lr 1e-4), one with half the learning rate (te lr 5e-5) and one without text encoder training (te lr 0). All three versions are usuable without having too much style bias. However for the version with full te traing I used epoch 30 and for the others epoch 20. Unfortunately I messed up and lost the epoch 20 file from full te training, so I can't compare directly. The style seems to bake in somwhat faster without te training. Use "@3d" in the negative prompt for less style bias. Showcase images have same prompt/model/style LoRA and seed for each version, so you can compare which version you like best.
trigger words: 1girl, rui \(pokemon\), orange hair, short twintails, blue eyes, black choker, blue jacket, purple shirt, white skirt, black socks, pink boots
style tags: 3d, video game screenshot
Feel free to comment, if you have something to say about the lora and share your images on the model page. Sharing your images on the model page gives the creator a small blue buzz bonus. But more important I like to see, what people do with my LoRas.
If you like the LoRa please have a look at the showcase pics and leave a reaction.


