Different styles of cover graphics can be referred to

Introduction: Fine-tuned optimized version, weakening the effect of Lora and other collapses, no antonyms will tend towards a gray color tone, adding quality words while increasing contrast will make the colors in the image more intense, and the output will also be more convergent. Everyone can come up with their own preferred ways to create graphics.

Beginner's Recommended Sentence: 1girl, white hair, cityscape, give it a try first

Hope everyone has fun playing, and I hope everyone explores more usage scenarios.

Share more images~!!

v1048

• This model is a 2.5D partially realistic style model based on sd xl1.0

• Recommended sizes: 768*1344, 1024*1024, 1024*1280, etc.

• Recommended steps: starting from 30

• Recommended sampling: [Euler a] [DPM++ 3M SDE Exponential]

• Antonyms recommendation: For images without antonyms, it's marked as [none] (malformed hands, poorly drawn hands, mutated fingers:1.4)

• cfg scale: starting from 3.5

• Updated on May 28, 2024, I will strive to iterate and improve

• Enlarging recommendation: Use the image-to-image tool for enlargement processing, maintain consistency in sampling and output, steps should be 1.5-2 times the output, redraw range 0.1-0.2

• Note: When doing full-body open ad face repair, recommended: [face_yolov8n_v2.pt], for batch running, consider enabling ad, most of my high-resolution images are processed using the Ultimate SD upscale enlargement, with enlargement algorithm [4x-UltraSharp]  

Just a brief introduction to 2 routes:

Eluex Real World XL leaning towards realism

Fantasy Hacker XL leaning towards special effects

——————————————————————————————————————

Model Usage Statement:

1. Do not host this model or its derivative versions (such as fusion model versions) on websites or applications intended for profit or fundraising. If you need to use this model and its derivative versions for commercial purposes (such as generative services, image sales, posting images on short video platforms, or using images in publications), please contact the original author for authorization.

2. Images generated by this model must not be sold directly without sufficient manual modification to make them independent works.

3. Do not use this model to intentionally create or distribute illegal or harmful content. Please ensure that the model is used for positive and constructive purposes, complying with legal and ethical standards.

4. This model and the images it generates are for personal entertainment, research, and interest exchange purposes only, commercial use is prohibited.

The user will be responsible for any legal consequences, and the original author will not assume any responsibility.

This statement applies to all versions, and please credit the original author when using fusion models. Thank you for respecting and understanding the model maker.

Email: [email protected]

Danyao Shifang-AIGC Exchange Group: 261454498

——————————————————————————————————————