F.1_UI Graphic Design 2.5D Illustration_ Foods

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 for internet commerce, UI illustrations, graphic design, commercial picture books, etc., with a 2.5D illustration style.

This batch of materials is quite large, and one Lora can't finish it all. Moreover, training a large CK model is not enough, so I trained several Loras separately according to different concepts. The art styles are the same, but the concepts are different. This series includes: business office, animals and plants, food, and sports. I will train and test them separately in the next few days and publish them respectively.

Business office:https://civitai.com/models/1629875/f1ui-graphic-design-25d-illustrationbusiness-office

Animals and plants:https://civitai.com/models/1632893/f1ui-graphic-design-25d-illustration-animals-and-plants

Exercise:https://civitai.com/models/1648540/f1ui-graphic-design-25d-illustration-sports

.

Recommended graphic size: The minimum single side of the image should be >=1024.

Trigger words: A picture in the style of UGD_f. After testing, it doesn't make much difference whether to use it or not. If the elements of the original picture are unpopular, you can add it if you don'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.

Model weight: 0.8. Different weights will have different effects.

CFG: 3.5

CLIP: If the limb damage is severe, adjust the clip, either 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、商业绘本等的Lora，风格为2.5D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。该系列为：商务办公、动植物、食物、运动，分别在后边几天训练测试好分别发布。（链接在英文版那）

.

推荐图形尺寸：图片最小单边>=1024

触发词：A picture in the style of UGD_f，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

模型权重：0.8，不同的权重有不一样的效果

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.

参考提示词示例：

提示词建议用自然语言描述，可以用大语言模型润色一下，不要指代不明，ai会随意发挥。

提示词一：A picture in the style of UGD_f，A delightful breakfast scene featuring a slice of French toast topped with fresh berries,sliced cucumber and lime wedges

提示词二：the center of the image is a large vertical striped purple and white bucket, on which "fried chicken" is written in bold black letters, the bucket is filled with several pieces of crispy brown fried chicken, and some chicken pieces are slightly overlapping, to the right of the bucket is a purple cup, filled with dark soda, paired with a purple and white striped straw, in the foreground, there is a white plate, on which two pieces of fried chicken are placed, and one of them can be seen to have a layer of pink meat, in the lower left corner, there is a white napkin with purple stripes, the background is a simple white gradient, scattered with faint gray star-like glitter

 .

[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.