Skip to content
ModelListedExternal
Download

Wanwan (Wanko) - OnlinePetClub

Hey everyone, here's a character model of Wanwan from Onlinepetclub. I came across her design and really liked it, so I decided to create this .

KindLORABase modelAnimaVersionBgrade

Model source

Kind
LORA
File size
66.2 MB
Base model
Anima
Version
vAnima V1
Updated
Oct 22, 2026
Downloads
33
Source
Civitai

Source description

Training Information (Anima DiT)

  • Output Name: bf16_Anima_Char_Wanwan_Retrain

  • Network Module: networks.lora_anima

  • Epochs: 12

  • Max Train Steps: Auto (Epoch)

  • Learning Rate: 0.0001

  • Text Encoder LR: 5e-05

  • Optimizer: AdamW8bit

  • Mixed Precision: bf16

  • LR Scheduler: constant

  • LR Warmup Steps: 0

  • Rank: 16/16 (Dim, Alpha)

Anima Arguments:

  • timestep_sample_method: logit_normal

  • discrete_flow_shift: 3

  • weighting_scheme: logit_normal

Dataset Info (dataset.toml):

  • Batch Size: 2

  • Resolution: 1536x1536

  • Steps (calculated): 528

  • Bucketing: True

Datasets Parameter:

  • Anime : images: 13 | repeats: 4 | keep_tokens: 1 | flip_aug: False | shuffle_caption: False

  • 2_chibi : images: 5 | repeats: 1 | keep_tokens: 1 | flip_aug: False | shuffle_caption: False

  • Anime. no agoe : images: 5 | repeats: 4 | keep_tokens: 1 | flip_aug: False | shuffle_caption: False

  • Chibi no agoe : images: 7 | repeats: 1 | keep_tokens: 1 | flip_aug: False | shuffle_caption: False

  • Anime new : images: 2 | repeats: 2 | keep_tokens: 1 | flip_aug: False | shuffle_caption: False

Sources

1 source
CivitaiPrimaryVersion 3203935
civitai.com/models/1836201

Verified Aug 18

Model artifacts

1 artifact

bf16_Anima_Char_Wanwan_Retrain.safetensors

safetensors · BF16 · 66.2 MB · SHA-256 9fd3257d3b41…8cec · Civitai

Download

Source excerpts

1 excerpt

Source context: 406 downloads · Type LORA · Base model Anima