- While testing and tweaking with parameters for training, I came up with this model, it's trained using 20 images(v1) 40 images(v3) and does a pretty nice job so I decided to upload it here. It's tricky to get her backpack, so some patience, prompting and searching seeds until it looks nice. The base model for training was AbyssOrangeMix2, 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.
- I'm planning an update with 40 images for training, stay tuned. done(v3)
- 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!