V-Pred version now available!
This DORA is design to recreate the style of Shounen Zoom by Shigeru. This new version is much better at recreating the style and gives you more control over style elements. Read the usage notes for each version below. A Hires fix pass is recommended for all versions for best results.
All sample images were created directly out of ReForge UI with a Hires Fix pass. No inpainting or ADetailer was used.
Now that there is support for DORAs on most generation platforms, all future releases will be in the DORA format. These can be used exactly the same way as a LORA.
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 available on Hugging Face and on CivitAI: https://civitai.com/models/461407?modelVersionId=1182425
USAGE NOTES:
For both V7 versions it is recommended to use full 1.0 strength. Both versions use special style tags that were introduced starting in V6:
2020s, 2015s, 2010s - These will denote the era of style to use. "2010s" is almost exclusively watercolor and "2015s" is an intermediate style.
watercolor, textured paper - These tags, used in conjunction with "2010s," should give a unique watercolor shaded style. Note that for V4 and V6, this is tagged as "source_watercolor" For some reason, the NoobAI V-pred version is not as good at this style. I recommend sticking to NoobAI Epsilon if you want this style.
manga, monochrome, screentones - These tags will create a black and white manga style. This is most effective on the NoobAI version and has mixed results on the Pony version.
PONY:
When using Pony, no trigger words are needed, but you should pick a style era. This DORA was trained on Autism Mix. If you are using a different checkpoint, you may need to use a higher strength to maintain the style.
Recommended positive prompt:
score_9, score_8_up, score_7_up, score_6_up, source_anime, 2020s/2015s/2010s
Recommended negative prompt: (you can adjust "hands" and "fingers" as needed)
source_pony, (hands:1.1)
NoobAI:
For NoobAI, the V-Pred version was trained on NAI V-pred 1.0 and the Epsilon version on NAI Epsilon-pred 1.1-Version, please use the correct checkpoints for best results. When using the NoobAI version, you should use the trigger word "shounenzoom-style" and an era.
Recommended postive prompt:
masterpiece, best quality, shounenzoom-style
Recommended negative prompt: (you can add "hands" and "fingers" as needed)
worst quality, bad quality, screenshot, sketch, jpeg artifacts
NSFW NOTE: This dataset contains many NSFW images. If you do not want NSFW make sure you actively prompt away from it.
TAGGING NOTES:
The dataset contains over 500 images (~40% of which are crops/flops) that were cleaned up and decensored by hand.
Score_9/"masterpiece" and score_8/"best quality" are the most recent works by the artist.
Score_7/"good quality" and score_6/"average quality" are older works and manga scans