Sign In

F.1_Commercial UI_Minimalist Graphic Design Illustration

31

244

1

26

Verified:

SafeTensor

Type

LoRA

Stats

244

1

7

Reviews

Published

May 27, 2025

Base Model

Flux.1 D

Training

Steps: 7,800
Epochs: 20

Usage Tips

Strength: 0.8

Hash

AutoV2
02594A14E8
default creator card background decoration
Vidu Contest Participant

dyrice

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Model Description: This is a Lora for Internet business, UI graphic, work, daily life, etc., with a simple style. After testing hundreds of pictures, the style is fairly stable.

Recommended graphic size: picture minimum unilateral>=1024

Trigger word: A picture in the style of mgd_ilstrn, not a trigger word but similar to the trigger word, test down with no difference, if the picture element minority, do not follow can add try.

Sampling algorithm: Euler a

Scheduler: simple, normal or beta

Sampling times: about 30 steps, some elements of the picture are broken and unclear, and the number of steps is increased.

Recommended Model Weight: 0.8

CFG:3.5

CLIP: clip, 1 or 2 if limb collapse is severe;clip parameter is not fixed

HD fix: Zoom algorithm recommended: R-ESRGAN_4x+Anime6B,4x-AnimeSharp,

Redraw range: 0.3 (the smaller the image, the bigger the imagination)

模型说明:这是一款用于互联网商业、UI平面配图、工作、日常生活等的Lora,风格比较简约。几百张图测试下来,风格还算稳定。

推荐图形尺寸:图片最小单边>=1024

触发词:A picture in the style of mgd_ilstrn,不是触发词但和触发词作用相似,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 prompt example:

It is suggested that the prompt words be described in natural language, which can be polished with large language models.

提示词一:it depicts two people sitting in front of a large computer screen displaying code, with a coffee cup on the table, the background of the picture is white, and there is a window in the upper right corner showing a red sun, on the left side of the picture, a man and a woman seem to be sitting at a table, both wearing blue shirts and facing the same direction, the man is facing the audience, and the woman is facing away from the audience, the man has a short black hairstyle, while the woman has a long black bun, both of them are looking at the computer screen.

提示词二:This vibrant digital illustration depicts a cheerful young woman with long, flowing red hair, wearing a blue shirt and purple pants. She is mid-air, holding a white smartphone in her right hand, waving with her left. The background is a lively grid pattern filled with various fruits: watermelons, pineapples, strawberries, and kiwis. Her red sneakers match the vivid colors of the fruits, creating a playful, energetic scene. The style is cartoonish with bold lines and bright, saturated colors.,A picture in the style of mgd_ilstrn

[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.