Anime Figure (Style) [Illustrious & Pony & SD1.5] - v1.0
Recommended Prompts
figure, ((masterpiece, best quality)), cowboy shot
Recommended Negative Prompts
EasyNegativeV2, bad-hands-5, blurry, bad anatomy, poorly detailed, (worst quality, low quality:1.4)
Recommended Parameters
samplers
steps
cfg
clip skip
resolution
other models
Recommended Hires (High-Resolution) Parameters
upscaler
upscale
denoising strength
Version Highlights
This a style Lora but it knows a bunch of characters and can get 90% of the details correct without character Loras. This is just extra don't expect perfect characters without a character Lora. A few of these No-Lora characters are in the examples.
Also it can make Chibi characters -- but I didn't test this very much.
Trained on: 585 images
Training Model: AnyLoRA_noVae_fp16-pruned
flip_aug: False
Num of Repeats: 5
Unit is Epochs or Steps: Epochs
Number of Epochs or Steps: 10
Training Batch Size: 2
Total Steps: 14640
Resolution: 512
Network Dim: Dim=32; Alpha=16
Lora Creation Process took: 2:36:08
Creator Sponsors
Help fuel my passion! Even $1 makes a difference. ☕ https://ko-fi.com/citronlegacy
Check out all the Art styles I’ve made: https://civitai.com/user/CitronLegacy/models?tag=style
Help fuel my passion! Even $1 makes a difference. ☕ https://ko-fi.com/citronlegacy
Check out all the Art styles I’ve made: https://civitai.com/user/CitronLegacy/models?tag=style
This is trained on almost 600 pictures of anime figures.
Model Details
Model type
Base model
Model version
Model hash
Trained words
Creator
Discussion
Please log in to leave a comment.








