NOTE: ALL CHARACTERS IN THE IMAGES ARE ADULTS.

How to Use This Model

USE THEM SIMULTANEOUSLY. In this case, you need to download both cirno_touhou.pt and cirno_touhou.safetensors, then use cirno_touhou.pt as texture inversion embedding, and use cirno_touhou.safetensors as LoRA at the same time.

それらを同時に使用してください。この場合、cirno_touhou.ptとcirno_touhou.safetensorsの両方をダウンロード する必要があります。cirno_touhou.ptをテクスチャ反転埋め込みとして使用し、同時にcirno_touhou.safetensorsをLoRAとして使用してください。

同时使用它们。在这种情况下，您需要下载cirno_touhou.pt和cirno_touhou.safetensors这两个文件，然后将cirno_touhou.pt用作纹理反转嵌入， 同时使用cirno_touhou.safetensors作为LoRA。

(Translated with ChatGPT)

The trigger word is cirno_touhou, and the recommended tags are masterpiece, best quality, highres, solo, {cirno_touhou:1.10}, blue_hair, bow, hair_bow, short_hair, ice_wings, wings, ice, blue_bow, blue_eyes, bangs, blush, smile, open_mouth, hair_between_eyes, ribbon.

How This Model Is Trained

This model is trained with HCP-Diffusion. And the auto-training framework is maintained by DeepGHS Team.

Why Some Preview Images Not Look Like Cirno Touhou

All the prompt texts used on the preview images (which can be viewed by clicking on the images) are automatically generated using clustering algorithms based on feature information extracted from the training dataset. The seed used during image generation is also randomly generated, and the images have not undergone any selection or modification. As a result, there is a possibility of the mentioned issues occurring.

In practice, based on our internal testing, most models that experience such issues perform better in actual usage than what is seen in the preview images. The only thing you may need to do is fine-tune the tags you use.

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

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

Why Not Just Using The Better-Selected Images

Our model's entire process, from data crawling, training, to generating preview images and publishing, is 100% automated without any human intervention. It's an interesting experiment conducted by our team, and for this purpose, we have developed a complete set of software infrastructure, including data filtering, automatic training, and automated publishing. Therefore, if possible, we would appreciate more feedback or suggestions as they are highly valuable to us.