• YOU CAN ALSO FIND THIS MODEL ON HUGGINGFACE HUGGINGFACE.
• THIS MODEL HAS ONE FILE. ENJOY IT.
• The trigger word is chunyuan, and the recommended tags are best quality, masterpiece, highres, solo, {chunyuan:1.15}, long_hair, animal_ears, black_hair, grey_hair, multicolored_hair, halo, streaked_hair, blush, bangs, breasts, small_breasts, brown_eyes, very_long_hair, striped, vertical_stripes, hair_between_eyes..
• Recommended weight is 0.5-1.15.
• Images were generated using a few fixed prompts and dataset-based clustered prompts(TODO). Random seeds were used, ruling out cherry-picking. What you see here is what you can get.
• No specialized training was done for outfits. You can check our provided preview post to get the prompts corresponding to the outfits.
• This model is trained with 398 images.

How to Use This Model

THIS MODEL HAS ONE FILE. ENJOY IT. In this case, you just need to download .safetensors.

このフォルダにはファイルが1つあります。それらを楽しんでください この場合、ダウンロード.safetensorsできます。

这个模型有一个文件。玩的开心。 在这种情况下，您只需下载.safetensors这个文件。

이 모델은 파일이 하나 있습니다. 즐기세요. 이 경우, .safetensors을 다운로드하시면 됩니다.

(Translated with ChatGPT)

How This Model Is Trained

This model is trained with kohya-ss' sd-script. Using auto-fulled param by i1998. And the auto-training framework is maintained by DeepGHS Team.

And the WebUI Panel provid by LittleAppleWebUI

Why Some Preview Images Not Look Like Chunyuan

Our kohya training process only uses auto fill parameters, so you should contact the author of the parameters.

You may need to do is adjusting the tags you are using, or give up.

I Felt This Model May Be Overfitting or Underfitting, What Shall I Do

Our model has been published on huggingface repository - AppleHarem/chunyuan, where models of all the epochs are saved. Also, we published the training dataset on huggingface dataset - AppleHarem/chunyuan, which may be helpful to you.

This model's greatest strengths lie in recreating the inherent characteristics of the characters themselves and its relatively strong generalization capabilities, owing to its larger dataset. As such, this model is well-suited for tasks such as changing outfits, posing characters, and, of course, generating NSFW images of characters!🤬

For the following groups, it is not recommended to use this model and we express regret:

1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
6. Individuals who feel that writing a WebUI is meaningless or impatient.