Download
1 variant available
Epoch-8 checkpoint (3200 steps). Trigger lin_wanxing; optional lwx_default.

70 1 2 3 4 5 6 7 8 9
640 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
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
Original character LoRA for Lin Wanxing / 林晚星, trained on the Anima base model (anima-base-v1.0).
Trigger word: lin_wanxing — use the token exactly as written, underscore included.
lwx_default is a secondary token for the character's default outfit (present in 4 of 40 captions).
Trained at 1024×1024 with bucketing, 40 images × 10 repeats, network dim 16 / alpha 8, AdamW8bit at 1e-4 with a cosine schedule and 200 warmup steps. This release is the epoch-8 checkpoint (3200 steps), not epoch-10.
ComfyUI-converted (*_comfy.safetensors).
