Training model: Animagine XL V3.1, https://civarchive.com/models/260267/animagine-xl-v3

Recommended Image Resolution: 1024+

Weight: 0.6-1.0, I still cannot fix distorted image generation in V1.12. Will try to fix it soon.

Prompts: ponytail, brown hair, Bangs, brown eyes, short hair, half-closed eyes (optional)

Recommended to use these prompts also for anime image generation:

anime screencap, high quality anime 2d color, 2d, Accurate describe shapes, beautiful face, expressive eyes, (plain anime style), natural lighting, light particles, cinematic angle, (masterpiece), (best quality), (ultra-detailed), very aesthetic, illustration, perfect composition, intricate details, moody lighting, light rays, depth of field, cowboy shot, cinematic angle, establish

Recommended Setup: Steps: 24, cfg: 7.0, Sampler: Euler A karras (as of V1.12)

Result may not be consistent, feel free to improve this LORA by retraining it, but ask me beforehand. Use Animagine XL V3.1 for best results.

This is my first time making LORA, please give me some feedback and suggestions for improvement :)

say no to ntr