This model was originally uploaded to HuggingFace / Civitai. If it's yours, please contact us so we can transfer it to your account!
Update: Complete remake with better dataset and parameters after much learning!
LoRA trained with images from artist TanDo (https://www.pixiv.net/en/users/5899771), follow and support the artist!
This is a complete revamp of the first LoRA I posted. It is completely revamped and it is able to achieve great results! See for yourself the example images.
Trained on NAI and should work with most anime models.
Hope you enjoy! Please rate and give your feedback!
Download (8.9 MB)
Download available on desktop only
🙈 Heads up! This is not an AI model, but a model addon. This file doesn't produce images by itself – it needs to be used in combination with one of our image AI models. Learn how to do it with our crash course.
Popularity
750
160
Info
Base model: SD 1.5
Version v1.0: 1 File
tandoStyle_v10.safetensors
(8.89 MB)
To download these files, please visit this page from a desktop computer.
About this version: v1.0
Trained using AbyssOrangeMix2 model
23 images, handpicked, not cropped, added .txt captions (WD1.4)
10 repeats, 20 epochs, batch size 2
LR: 0.001, Unet LR: 0.001, Text encoder LR: 0.0005
Net dim: 8, Net alpha: 8
Runtime ~15min
2 Versions
😥 There are no TanDo - Style v1.0 prompts yet!
Go ahead and upload yours!
