NOTE: The sample gallery has been sanitized to comply with Tensor's new content standards.

This DORA is designed to recreate the style of the artist Fujimodoki. No trigger words needed, but read the description of the score tags for details. HiRes Fix is recommended for the best results.

This is my first ever DORA. Now that there is support for DORAs on most generation platforms, I've decided that the quality increase is worth it. All future releases will be in DORA format and I will probably update my previous releases to this format, as well.

This artist is not currently active, but please support the original artist wherever possible so they can continue to produce their art. Without them, LORAs such as these would not be possible.

This model is also backed up on Huggingface and is available on CivitAI: https://civitai.com/models/678446/fujimodoki-style

USAGE NOTES:

This LORA was trained on AutismMix and is recommended to use it at full 1.0 strength. If you are using a different checkpoint, you may need to use a higher strength to maintain the style. Most images were tagged with "source_anime" and scores 6-9. Some of the artists newest images that were made in collaboration with Kamin were tagged with "source_cg"

TAGGING NOTES:

Images were ranked in scores 6-9 as well as given the "source_anime" or "source_cg" tag. Many source images were low-resolution and had to be upscaled using AI. Any images that may have shown artifacting from the upscale process were tagged with "ai-upscale" so it may be helpful to put that in the negative if you are having issues.

Scores 9 and 8 images are the most detailed and newest works with "score_9" having the most detailed shading and best anatomy.

Score 6 and 7 images are lower-detailed works with less worse anatomy and shading. The source images have some varying skin tones so you may need to prompt "pale skin" or "saturated colors" in the negative as necessary.

Please do not violate the content policy