Type | |
Stats | 2,494 |
Reviews | (135) |
Published | Mar 25, 2023 |
Base Model | |
Training | Steps: 1,500 Epochs: 4 |
Usage Tips | Clip Skip: 1 |
Trigger Words | yotsugi_ononoki ononokihat yotsugiononoki |
Hash | AutoV2 887AED4951 |
- Again messing with my workflow, I got an interesting result, this time Yotsugi Ononoki! And with this, my three best girls of Monogatari collection as LoRA models is done! In the future I will update them all and make an 3in1 collection, but this doesn't mean it's over, there's many more of Monogatari that I want to make! The model was trained using 75 images. It's tricky to get her hat and V posing to look right, so as normal patience, prompting and searching seeds until it looks nice. The base model for training was AnyLora, you should test it in different models and choose one you find better. Needs a decent prompt.
- Don't forget to favorite to get notified when there is any update.
- Recommended weight 0.7 to 0.9, and HiResFix. Also fix the LoRA file name if you use my prompt.
- Note that I use XFORMERS and Negative TI's, so if you're trying to recreate my example images, it will be different.
- If you use it and post on Twitter or Pixiv, please tag me or in the comments, I want to see your creations! You all are free to comment, I appreciate any advice to make it better. Thanks!