This is a lightweight model designed specifically for creating wool yarn art pieces, with a size of only about 18MB. Lora can generate delicate and lifelike wool yarn textures and patterns while maintaining high performance. Whether it's traditional knitting patterns or modern art designs, Miaokaya Wool World can easily handle it without the need for complex prompts.

For Lora's weight, it is recommended to set it at 1. If the generated item does not have the wool effect, please give weight to the trigger words. Do not adjust Lora's weight directly. Adding weight to Lora's trigger words means, for example, if my trigger word for Lora is "mkyangmaoxian," I would add parentheses outside the prompt word like this: ("mkyangmaoxian"). If the effect is still not enough, add two parentheses: (("mkyangmaoxian")) or add weight within the parentheses ("mkyangmaoxian: 1.1"), but generally it is not recommended to use weights with numbers.

The image parameters I used are from sd-webui-forge for image generation.

Here are the image parameters I used under sd-webui-forge.

Model Usage Statement

1. You are not allowed to host this model and its derivative versions (such as merged model versions) on websites/apps intending to earn income or donations. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, publishing images publicly on short video platforms or publications, etc.), please contact me through the website.

2. You are not allowed to directly sell the images generated by this model unless you have made enough manual modifications to the image to fully establish it as your personal work in a legal sense. If you violate this clause, you are personally responsible for all legal consequences, for which I shall not be held responsible.

3. You cannot intentionally use this model to create or share illegal or harmful content for dissemination. Please adhere to ethical standards and use this model for positive and constructive purposes.

Model feedback technical exchange QQ group: 377209248

This model does not contain any real human material image sources, and training code is sourced from the internet. The model is only used for scientific research and interest exchange.