如果大家有喜欢或推荐的风格，请留言，合适的话有时间会加到后续版本。仅业余爱好折腾，如有版权问题请联系！

If there is any fantacy styles you like, please leave your comments here. Would add it to the future version if possible. This Lora is only a hobby toss, if have any copyright issues, please contact me!

基于MJ精致图片训练的梦幻童话风格Lora，可以用较短的提示语生成相应风格的梦幻图片。欢迎试玩！

Some fairy tale styles trained on midjouney picutures. We could generated specific style picture with a short prompts. Just try and enjoy!

1. paper cut. keyword: paper-cut [craft/art painting]. recommended weight:~0.7.

2. super cute animal. keyword: fairy tale. recommended weight:~0.7.

3. delicate scene/CG rendering. keyword: delicate scene. recommended weight:~0.7.

4. rime. keyword: rime. recommended weight:~0.7.

5. crystal flower. keyword: transparent/crystal . recommended weight:0.3-1.0.

6. others. keyword: close-up display/ animie 1gir/fantacy painting.

2023/5/10 Update V2 version: included papercut styles based on 60 incremental papercut pictures.

1. two styles: craft and art paiting. key words: paper-cut [craft/art painting].

2. with/without photo-frame, key words: photo-frame/no-frame.

3. with/without mask, key words: [shape] mask/no-mask.

2023/5/3 Update v1s version: enlarge texture embedding dimension and training batch size in AIStudio Platform(https://aistudio.baidu.com) providing free GPU resources. Tag expression is more accurate and picture seems more clear and transparent.