This style lora is trained on images by KYHU, the old pen name of artist IAHFY. The dataset mainly consists of images of Korra and Asami, but it also works good for other characters. The images have monochrome or low detailed backgrounds. So this lora is best suited for generating characters without detailed backgrounds for Illustrious. Since Anima seems to be better at generating detailed background, you can try if it does better there, but I haven't really tested it. Works nice with additional style tags like "monochrome", "sepia" or "sketch". All versions are trained with the same dataset and captions. If you want to support the artist, you can find options here.
trigger word: kyhustyle
additional style tags: monochrome, sepia, lineart, sketch
character tags: asami sato, korra
Feel free to comment, if you have something to say about the lora and share your images on the model page. Sharing your images on the model page gives the creator a small blue buzz bonus. But more important I like to see, what people do with my LoRas.
If you like the LoRa please have a look at the showcase pics and leave a reaction.
Description
This is the first ZIT LoRa I am publishing. It is trained with the same dataset and same danbooru tag style captioning as the illustrious version.
It can be used with tag style prompting, but I noticed that natural language prompts or mixed prompts seem to work better with Zimage Turbo. So using "detailed drawing in kyhustyle of" or "digital art in kyhustyle of" at the beginning of your prompt followed by your main subject should be used instead of just the trigger word "kyhustyle".
I recommend a weight of 0.5-1.0, but at values close to 1.0 the bias towards korra gets pretty strong, since she is in most of the images in the dataset.
For the showcase pics I used an fp8 quantized version of base Zimage Turbo, so they look a bit different from the illustrious showcase pics using a finetuned checkpoint.
trigger words: kyhustyle, korra