In the previous article, I shared with you how to convert line drawings of pictures into Wensheng drawings.
The conversion of image to line drawing can also be achieved by using the method of image generation. Let's first look at the effect of using the method of image generation to convert image to line drawing.
1. How to convert pictures into line drawings
[Step 1] Upload the raw image with white background
Here we use Meitu XiuXiu to create a pure white background image. Upload this white background image in the Image Generator menu.
[Step 2]: Selection of large model
Recommended here: majicMIX realistic V7.
Model download address (you can also get the network disk address at the end of the article)
LiblibAI:https://www.liblib.art/modelinfo/bced6d7ec1460ac7b923fc5bc95c4540
Step 3:Prompt wordWriting
Positive prompt words
Prompt：lineart,line drawing,sketching,blank and white,clean white background,masterpiece,best quality,fine detail,8K,UHD,wallpaper,
Prompt word: line art, line drawing, sketch, blank and white, clean white background, masterpiece, best quality, fine details, 8K, UHD, wallpaper
Reverse prompt word
negative
Related parameter settings
- Sampler: Euler a
- Sampling iteration number: 20
- Image width and height: 512*768 (same as the original image to be transferred)
- Prompt word guidance coefficient (CFG): 7
- Redraw amplitude: 0.75
[Step 4]: ControlNet settings
The relevant parameter settings are as follows:
- Control Type: Select "Lineart"
- Preprocessor: lineart_realistic
- Model: control_v11p_sd15_lineart
- Control weight: 1
【Step 5】Image generation
Click the [Generate] button and let’s take a look at the final generated image effect.
 |
 |
2. Related comparison
(1) The image generation method does not need to use the loar model of the line drawing type. I have tried using lora Anime Lineart/Manga-like, and I personally feel that the effect is not very good. However, different people may have different opinions. You can refer to the following pictures for comparison.
|
No loar used |
Use loar |
|
|
 |
(2) According to current tests, the effect of transferring real-life pictures is relatively good. However, when transferring line drawings of architectural pictures, the lines are very thin, which makes the pictures look unclear.
 |
 |
After adding the AnimeLineart/Manga-like loar, the image clarity has improved. However, there is still room for optimization and improvement in the architectural re-drawing.
|
No loar used |
Use loar |
 |
 |
(3) I personally feel that the method of realizing the picture-based drawing is better than the method of realizing the text-based drawing. The lines are clearer and simpler, and the line drawing effect is more realistic.
|
Vincent Figure |
Figure 1 |
 |
|
Okay, that’s all for today’s sharing. I hope that what I shared today will be helpful to you.
The model is placed in the network disk, and those who are interested can take it!
https://pan.quark.cn/s/b3df771404e2