Type | |
Stats | 985 6,806 34 |
Reviews | (110) |
Published | Sep 11, 2023 |
Base Model | |
Training | Steps: 4,400 Epochs: 11 |
Usage Tips | Clip Skip: 2 |
Trigger Words | flandre_scarlet_touhou blonde_hair, wings, red_eyes, crystal, bangs, hat, one_side_up, ribbon, mob_cap, bow, blush, smile, vest, white_headwear, red_vest, ascot, hair_between_eyes, red_bow, red_ribbon, upper_body, hat_ribbon, yellow_ascot, short_hair |
Hash | AutoV2 1A1C854B2A |
NOTE: ALL CHARACTERS IN THE IMAGES ARE ADULTS.
How to Use This Model
USE THEM SIMULTANEOUSLY. In this case, you need to download both flandre_scarlet_touhou.pt and
flandre_scarlet_touhou.safetensors, then use flandre_scarlet_touhou.pt as texture inversion embedding, and use
flandre_scarlet_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、flandre_scarlet_touhou.ptとflandre_scarlet_touhou.safetensorsの両方をダウンロード
する必要があります。flandre_scarlet_touhou.ptをテクスチャ反転埋め込みとして使用し、同時にflandre_scarlet_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flandre_scarlet_touhou.pt和flandre_scarlet_touhou.safetensors这两个文件，然后将flandre_scarlet_touhou.pt用作纹理反转嵌入，
同时使用flandre_scarlet_touhou.safetensors作为LoRA。
(Translated with ChatGPT)
The trigger word is flandre_scarlet_touhou, and the recommended tags are masterpiece, best quality, highres, solo, {flandre_scarlet_touhou:1.10}, blonde_hair, wings, red_eyes, crystal, hat, ribbon, mob_cap, one_side_up, bangs, bow, smile, vest, white_headwear, ascot, blush, red_vest, red_ribbon, red_bow, hat_ribbon, hair_between_eyes, yellow_ascot, short_hair.
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 Flandre Scarlet 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/flandre_scarlet_touhou, where models of all the steps are saved. Also, we published the training dataset on huggingface dataset - CyberHarem/flandre_scarlet_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.