The model training set has a large number of steps, and its versatility is quite good. We hope everyone can download and generate it to support us, so we can save some computing power and electricity costs. Thank you!
.
Model Description:
This is a Lora used for Internet commerce, UI illustrations, graphic design, and business, etc. Its style is flat illustration.
This batch of materials is quite large, and one Lora can't finish it all. Moreover, the CK large model is not enough, so I trained several Loras according to different concepts. The art styles are the same, but the concepts are different. The remaining ones are: animals and plants, food, and sports, which will be released one after another in the next few days.
Animals and plants:https://civarchive.com/models/1632893/f1ui-graphic-design-25d-illustration-animals-and-plants
Exercise:https://civarchive.com/models/1648540/f1ui-graphic-design-25d-illustration-sports
Foods：https://civarchive.com/models/1649190/f1ui-graphic-design-25d-illustration-foods
.
Recommended graphic size: The minimum single side of the image should be >=1024.
Trigger word: This is a picture in the UGD style with an isometric perspective. After testing, there's not much difference whether to use it or not. If the elements of the original picture are not mainstream, you can add it if it doesn't follow the rules.
Sampling algorithm (Sampler): Euler a
Scheduler: simple, normal, or beta.
Sample frequency: About 30 steps. Some elements in the image are broken and not clear, so we need to increase the number of steps.
Recommendation model weight: 0.8
CFG: 3.5
CLIP: If the limb damage is severe, adjust the clip, 1 or 2; the clip parameters are not fixed.
High-definition restoration: Enlargement algorithm recommendation: R-ESRGAN_4x+Anime6B, 4x-AnimeSharp.
Redrawing amplitude: 0.3 (The smaller the value, the more it resembles the original image; the larger the value, the more it allows you to use your imagination.)
.
模型说明：
这是一款用于互联网商业、UI配图、平面设计、商业等的Lora，风格为扁平插画风格。
这一批素材集较大，一个Lora炼不完，炼ck大模型又不够，所以我根据不同概念分别炼了几个Lora，画风相同，只是概念不同。余下几个为：动植物、食物、运动，分别在后边几天分别发布。
.
推荐图形尺寸：图片最小单边>=1024
触发词：This is a picture in the UGD style with an isometric perspective，测试下来用不用差别不大，若生图元素小众，不遵从可添加试试。
采样算法（Sampler）：Euler a
调度器：simple，normal或beta
采样次数：30步左右，画面有些元素崩坏不清晰提高步数
推荐模型权重：0.8
CFG：3.5
CLIP：如果肢体崩坏严重就调clip，1或2；clip参数不是固定的
高清修复：放大算法推荐：R-ESRGAN_4x+Anime6B,4x-AnimeSharp,
重绘幅度：0.3（越小越像原图，越大越发挥想象）
.
Reference example of prompt words:
We recommend describing the keywords in natural language and polishing them with a large language model. Also, make sure there are no unclear references, as AI might interpret them differently.
提示词一：A simple and minimalistic flat illustration of a a young boy with short hair and glasses,seated at a desk,facing a computer screen,the background is includes various posters and notes,The design features a flat,vector-based style with a white background in the style of modern web UI design
提示词二：in the center of the picture is a woman with flowing long hair, who is writing in a notebook with a pen, she is wearing a blue top and posing in a side view, with her upper body facing the audience, the background is a pure white wall, on which there is a large rectangular screen displaying a blue and white interface, with a blank form on the screen, above her head, there are several smaller rectangular patterns floating, this woman looks like a young adult, with a slim figure and flowing long hair, and she is writing with a pen in her right hand
.
[Disclaimer]
1. In principle, this model is only for communication and learning, and the model and generated images cannot be used for commercial purposes.
2. The user shall handle any intellectual property disputes arising from the content generated based on this model on their own, provided that they comply with local laws and regulations and the terms of service.
3. Without the author's permission, you cannot integrate this model into any third-party software or services on your own.