SDXL 1.0 ArienMixXL Asians Like Asians Portraits

Use the figure facial repair plugin ADetailer: https://gitcode.net/ranting8323/adetailer

Refer to the suggested proportion for the design drawing!

Describe a broken hand, for example: hands placed in front of the chest

Content:

This version uses chatglm.cn for enhanced training in image recognition and improved sensitivity of natural language. You can refer to the following image example:

English Description:

This is a portrait photo of a woman. Her hair is brown, medium-short, slightly wavy, and looks very shiny. The makeup on the face is exquisite, especially the glitter at the corners of the eyes and cheeks, giving people a starry sky feeling. Her lips were painted with orange-red lipstick, which contrasted sharply with her fair complexion. She accessorized with a pair of sparkling earrings that matched the glitter on her face. The woman looked very sparkly and elegant in a silver sequined halter top. The background is dark, making her facial features stand out even more.

Therefore, I suggest you use intelligence to deduce the image elements you want and apply them to image generation.

In the case of NFSW, I provided the model with an appropriate degree but did not prevent its generalization in this area.

As I have not done any simplified image optimization, this version needs to combine some detailed descriptors and lighting effects to achieve better results.

Usage suggestion:

Negative cues: cgi, illustration, cartoon, deformation, distortion, disfigurement, poorly drawn, poor anatomy, anatomical errors, ugliness, deformation, blurring, noise, log, text

VAE: No external VAE required

Recommended sizes: 1200x900, 1024x768, 1280x768, 1356x1024, 1536x1024

Recommended sampler: DPM++ 3M SDE Karras

Recommended number of steps: 50-150

If you have any business needs, please contact me below

QQ Group: 895633778

Business cooperation email: 1269695709@qq.com

WeChat: 13353036335 (Please refrain from chatting)

Disclaimer:

All images generated by the model are created by the users themselves, and the model author has no control over the images generated by users. The model author is not responsible for any potential copyright infringement or unsafe images.

V5.0

Use Chatglm.cn for tagging, optimizing natural language sensitivity

V4.0

Added more antique styles and makeup

V3.0

Optimized texture of portraits, better faces, added more clothing, optimized lighting effects, optimized body proportions, no trigger words, ensuring stable dissemination of Asian people

V2

To optimize the normal dissemination of Asian people, change the underlying stereotypes of Asian people, can use comfyUI as an Asian refiner to gain Asian features.

V1.0

The test version is the first genuine portrait version of this series, without the need for VEA, can generate realistic Asian portraits through simple prompt text. It is important to note that as the refinement model cannot refine Asian characters well, it is not recommended to use the refiner for refinement, it can be directly refined to 1024x1024.