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 model designed for use in internet commerce, UI illustration, graphic design, and commercial picture books. The style is 2.5D illustration.
Due to the large volume of this asset pack, it was not feasible to train everything into a single LoRA. Training on a full checkpoint model didn't yield satisfactory results either. Therefore, I trained several separate LoRAs based on different themes. All share the same artistic style but differ in concept. The series includes: Business & Office, Animals & Plants, Food, Sports, which will be tested and released over the following days.
.
Business & Office LoRA:
https://civarchive.com/models/1629875/f1ui-graphic-design-25d-illustrationbusiness-office
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 image resolution: Minimum side >= 1024
- Trigger word: A picture in the style of UGD_anp — testing shows that using it or not makes little difference. If generating niche elements, try adding it if results are off.
- Sampler: Euler a
- Scheduler: Simple, Normal, or Beta
- Sampling steps: Around 30 steps. Increase step count if some elements appear distorted or unclear.
- Recommended LoRA weight: 0.8
- CFG (Classifier-Free Guidance Scale): 3.5
- CLIP: Adjust CLIP if limbs or details are distorted — try 1 or 2. This parameter is not fixed.
- High-resolution fix:
- Recommended upscaling algorithm: R-ESRGAN_4x+Anime6B, 4x-AnimeSharp
- Denoising strength (re-draw magnitude): 0.3 (lower values preserve more of the original image; higher values allow more creative variation)
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。
商务办公Lora：https://civarchive.com/models/1629875/f1ui-graphic-design-25d-illustrationbusiness-office
.
推荐图形尺寸：图片最小单边>=1024
触发词：A picture in the style of UGD_anp，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 mother panda and her cub sitting in a lush blue bamboo forest, in the center of the image is a large black-and-white giant panda with a calm expression, squatting on the ground with a small blue bamboo plant in its paws, bringing it to its mouth, the cub sits beside it, also holding a bamboo plant, the background is plain white, featuring silhouettes of tall, slender light grey bamboo stalks
提示词二：two animals, a blue corgi dog and a black cat, each tied with blue balloons, the dog has two blue balloons attached to it, and the cat has three blue balloons, floating in the air, the background features fluffy white clouds, the corgi and the cat look directly at the viewer with friendly expressions, their faces fluffy, with small noses and smiling looks
.
[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.