Koki'o is a collaboration between @epiTune and @Shiiro0
The recommended resolution is 1024x1496, but 832x1216 is completely fine (including reversed into landscape or slight variations). You will see a composition and fidelity difference between the two - depending on your goals, you might want to try both.
Illustrious models (due to their strong prompt following) respond better to negative tags compared to what you might be used to with Pony models. Examples of potentially useful negative tags you can try:
anatomical nonsense, artistic error, bad anatomy, bad arm, bad aspect ratio, bad ass, bad face, bad feet, bad hands, bad knees, bad leg, bad neck, bad perspective, bad proportions, bad reflection, bad vulva, different reflection, extra arms, extra digits, extra eyes, extra faces, extra legs, extra pupils, fewer digits, oversized limbs, wrong foot, wrong hand
Try to tailor what negative tags you use to your specific needs rather than always including them all. A trimmed down version that's suitable for general use is:
anatomical nonsense, artistic error, bad anatomy
These should be used in tandem with staple negative tags such as:
worst quality, bad quality, low quality, lowres
On the flip side, recommended positive tags are:
incredibly absurdres, highres, masterpiece, newest
But do note that certain art styles benefit from omitting masterpiece and newest.
These tags heavily lean into the refined and modern digital look, if you want to generate watercolor these might work against you. Likewise, if you're going for a retro look, avoid newest.
For a traditional art style you might want to include tags such as:
traditional media, painterly, good quality, average quality
Some tags that are useful for steering away from the default anime look include: POS: painterly, no lineart, blending
NEG: flat color, high contrast, anime coloring, limited palette, outline, ligne claire, lineart, oekaki, jaggy lines, dithering, pixel art, monochrome, greyscale, sketch, anime screenshot
https://civitai.com/articles/8818/illustrious-art-mediums https://civitai.com/articles/8817/illustrious-year-modifier-tags
Recommended settings:
Steps: 30-40 CFG scale: 4-6 Sampler: Euler a OR DPM++ 2M
Koki'o Illu is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Shiiro0. Derived from the powerful Stable Diffusion (Illustrious) model, Koki'o Illu has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Koki'o Illu is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, black and white, art.
With a rating of 0 and over 0 ratings, Koki'o Illu is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Koki'o Illu from here.
To use Koki'o Illu, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Koki'o Illu, check out our crash course in AI image generation.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.