20241114v3

Someone still remembers this hardworking girl?

Yoshino Koharu from SAKURA QUEST

Trigger Words: yoshinokoharu

Trained with Pony Diffusion V6 XL checkpoint.

I have set a moderation on the gallery, so the NSFW content may not appear.

Due to "flagged for review", many images will be delayed by many hours before they can be viewed.

The original style has been enhanced, and the bad hand's problem has also been improved to some extent.

Many of the images I post have had their facial details repaired using ADetailer

Problems

• Bad hands still existed.

Usage tips

• The model's output may heavily rely on the checkpoint.

• The character's face, eyes, and pupils can be repaired through ADetailer.

• You could find the example prompts from my post.

• My prompts are basically composed in the order of [character traits] + [style] + [expression] + [clothing] + [camera and action] + [background], and you can delete or modify them as needed.

• Recommended weight: 1~0.6, adjust as needed until the character's appearance meets your requirements.

• Upscale value recommendation is around 1.2~2.0, denoising strength is 0.2

20240901

The previous version was more prone to distorted limbs, hands, and movements, as well as messy lines, which have been corrected to some extent in this version.

However, when the background becomes complex, the lines in this version can also become messy.

I have removed many low-quality images from the dataset and also redrew some average quality images in high definition.

The training of this model and the images it generates are solely for learning purposes.

You could find the example prompts from the images above.

20240630v1

you could add 'anim style' to the prompt, which will make the output image style closer to the original anime style. Or add 'anim style' to the negative prompt to diversify the style of the generated images.

The model currently has a tendency to struggle with rendering hands accurately. Additionally, there are some tags that are not labeled precisely.

The model is prone to producing poor-quality images. The lines in the graphics are also easily disordered. I believe this is due to the insufficient cleaning of low-quality images in the dataset, and the number of images in the dataset needs to be increased. This could potentially improve the model's performance.

Looking forward to your comments and pictures.