ColorInk l Chinese color ink-SDXL

<<<V1.0 Version>>>

Remember to return the image! Example images are all generated locally with 4090 (N), the effect is different from online generation!

Recommended large models: SDXL Basic_1.0 or other XL large models like GhostXL (feel free to try different large models and return the image!)

https://www.liblib.ai/modelinfo/1fd281cf6bcf01b95033c03b471d8fd8

Recommended LoRa weighting:0.6-0.8

Trigger words:Chinese style color ink

Recommended prompting words:

Chinese style color ink (need to fill in trigger words), ink wash technique, fine detail, vintage texture, you can describe other parts yourself. For example:Traditional Chinese beauty, ink wash painting style, Beijing opera costumes, etc..

Welcome to add elements by yourself or use the cherished prompting words~

1. Its feature is the ability to generate colorful ink brush illustrations of characters and animals, with half-body effect being the best!

2. It is recommended to produce images with a resolution of about 1024 and then perform 1.5x HD restoration, Euler sampler is recommended~

Recommended negative prompting words:

Realistic, EasyNegative, (worst quality, low quality: 1.4), (depth of field, blur: 1.2), (greyscale, monochrome: 1.1), 3D face, cropped, lowres, text, (nsfw: 1.3), (worst quality: 2), (low quality: 2), (normal quality: 2), lowres, normal quality, ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly: 1.331), (duplicate: 1.331), (morbid: 1.21), (mutilated: 1.21), (tranny: 1.331), mutated hands, (poor draw hands: 1.5), blur, (bad anatomy: 1.21), (bad proportions: 1.331), bs, extra disfigured (1.331), (missing arms: 1.331), (extra legs: 1.331), (fused fingers: 1.61051), (too many fingers: 1.61051), (unclear eyes: 1.331), lowers, bad hands, missing fingers, extra digit, bad hands, missing fingers, (((extra arms and legs))), freckles, (white border: 2), nsfw

Sampling method: Euler a (others are fine too, but this one seems to give the best effect)

Iteration steps: 30 (up to your mood)

Recommended sizes: 1:1/2:3/3:2/3:4/4:3/9:16/16:9 (feel free to try other sizes)

Guided word coefficient (CFG): 7.0

HD resolution restoration: 4x-UltraSharp If there are images that meet the requirements, use high-definition enlargement, with a redraw magnitude of 0.3-0.4, or directly redraw with a magnitude above 0.5 for a lucky draw~

<Attention>

There is a chance of hand and body, limb issues when generating, multiple lucky draws are required!

- If conditions allow, it is recommended to download and use locally~

- Locally, I've added a note v1.1 (from the second round of training), so there is no need to worry about the suffix of the example image; just use it normally~

- For full-body characters or when the proportion is small, facial deterioration and blurriness may occur. Please enable ADetailer and select face_yolov8n for restoration!

- Some prompting words may not have obvious effects, and future versions will expand their universality;

——————————————————————————————————————

Model Usage Statement:

1. You are not allowed to host this model and its derivative versions (such as fused model versions) on websites/apps intended for earning revenue or donations. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, publishing images on short video platforms or publications, etc.), please contact me through the site;

2. You are not allowed to directly sell images generated by this model unless you have sufficiently modified the images to a degree where they can be deemed entirely as your personal work in a legal sense. If you violate this clause, any legal consequences will be your responsibility, and I will not be held liable;

3. You cannot intentionally use this model to create or share illegal or harmful content for dissemination, please abide by basic ethics and use this model for positive and constructive purposes.