Guofeng3

🚀 GuoFeng3 Model - Chinese Gorgeous Antique Style

The GuoFeng3 model is a Chinese gorgeous antique style model with a 2.5D texture, suitable for creating antique game characters. The third - generation model has made significant improvements, reducing the difficulty of use and adding various elements.

📄 License

This model is licensed under CC - BY - NC - SA - 4.0.

✨ Features

• Multiple Versions: There are various versions of GuoFeng3, each with its own characteristics and improvements, such as GuoFeng3.1 for portrait fine - tuning, GuoFeng3.2 for a balanced choice, and GuoFeng3.3 and GuoFeng3.4 with more updates and adaptations.
• Reduced Difficulty: The third generation greatly reduces the difficulty of getting started, making it easier for users to generate satisfactory results.
• Rich Elements: It adds scene elements and male antique characters, and other style elements to better adapt to different TAGs.

📦 Installation

1. Put the GuoFeng3.ckpt model into the SD directory.
2. This model comes with VAE. If your program does not support it, please remember to select any VAE file, otherwise the graphics will be gray.

💻 Usage Examples

Basic Usage

• Simple Configuration: The third generation greatly reduces the difficulty of getting started.
  • Keywords:

best quality, masterpiece, highres, 1girl,china dress,Beautiful face

- **Negative Words**:

NSFW, lowres,bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worstquality, low quality, normal quality,jpegartifacts,signature, watermark, username,blurry,bad feet

Advanced Usage

• If you also want to make the picture as good as possible, please try the following configuration:
  • Sampling steps: 50
  • Sampler: DPM++ SDE Karras or DDIM
  • Picture size: at least 1024
  • CFG: 4 - 6
  • Better Negative Words:

(((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly,pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed,blurry,bad anatomy,bad proportions,malformed limbs,extra limbs,cloned face,disfigured,gross proportions, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs,username,blurry,bad feet

- **Enriching Elements**: If you want to enrich the elements, you can add the following keywords:

Beautiful face,
hair ornament, solo,looking at viewer,smile,closed mouth,lips
china dress,dress,hair ornament, necklace, jewelry, long hair, earrings, chinese clothes,
architecture,east asian architecture,building,outdoors,rooftop,city,cityscape

Tips

• Red - eye Problem: After a day of testing, we found that many characters may have red - eye problems. We can try to add "red eyes" to negative words. Try to reduce CFG if the color is bright.
• Facial Collapse: If you experience facial collapse during the full - body image, it is recommended to delete the "full body" keyword or use the facial automatic repair plugin:
  • Foreign source address: https://github.com/ototadana/sd - face - editor.git
  • Domestic acceleration address: https://jihulab.com/xiaolxl_pub/sd - face - editor.git

📚 Documentation

Model Versions

Model Descriptions

• GuoFeng3: Original model
• GuoFeng3.1: Fine - tuned and repaired the portrait of GuoFeng3
• GuoFeng3.2: If you don't know whether to choose GuoFeng3 or GuoFeng2, you can use this version directly
• GuoFeng3.2_light: Through GuoFeng3.2, Lora based on Noise Offset training is integrated to enable the model to draw more beautiful light and shadow effects (Lora: epi_noiseoffset/Theovercomer8's Contrast Fix)
• GuoFeng3.2_Lora: Guofeng3.2 Lora version
• GuoFeng3.2_Lora_big_light: Guofeng3.2_light Lora Version Dimension Increase Version
• GuoFeng3.2_f16: Guofeng3.2 semi - refined version
• GuoFeng3.2_light_f16: Guofeng3.2_light semi - refined version
• GuoFeng3.3: This version is a major update and improvement based on 3.2, which can adapt to full bodies. Even if your tag is not good, the model will automatically modify the screen, but the faces produced by the model will be quite similar. This model doesn't seem to require supersession. The recommended picture size is 768 * 1024, and the clarity is quite good. It is recommended to use vertical pictures, and horizontal pictures may not be clear. Euler a is sufficient. (DPM++ SDE Karras, DDIM is also good)
• GuoFeng3.4: This version has undergone new training to adapt to the full - body image, and the content is significantly different from previous versions. At the same time, the overall painting style has been adjusted, reducing the degree of overfitting, allowing it to use more Lora to adjust the screen and content.

Second - Generation Model

The second - generation model performs better in terms of characters and big - head photos. If you have this need, you can try it: https://huggingface.co/xiaolxl/Gf_style2

⚠️ Important Note

• The author solemnly declares that this model is prohibited from being used for training style models based on the portraits of celebrities and public figures, as this will cause controversy and have a negative impact on the development of the AI community.
• It is noted that the training materials of this model do not contain any real - person materials.

📚 Examples

(You can find the original image in the file list and put it in WebUi to view keywords and other information)

New Release

GuoFeng4 based on SDXL has been released! : https://huggingface.co/xiaolxl/GuoFeng4_XL