est quality,ultra high res,1girl,solo,full body,JK,ponytail,white hair,red eyes,expressionless,off shoulder,sneakers,short shorts,street,city,
(masterpiece), (best quality), (intricate_details:1.1), (finely detailed:1.4), (distinct_image:1.2), (cafe background), 1girl, cute, (face focus), shiny red eyes/black hair, cat ears, vine, smooth lighting, shirt,
extremely detailed CG unity 8k wallpaper, masterpiece, best quality, ultra-detailed, an extremely delicate and beautiful, night, dark, dim candlelight, candle, messy study room, many books, grimoire, book stock, magic girl, sleepy, head rest, black robe, vase, finely detail,, masterpiece, best quality,
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

About the model name:

Lou Andreas-Salomé is a legendary woman in 19-20 century,and it's also one important charactor of my own project——PROJECT SHADOW.

定制模型的初衷便是为了有一款符合我内心中对裂影世界观画风的专属模型,有许多方面并不是为了达到普世意义上的最优解,而是符合我自身需求的最优解,如:

1比传统二次元画风稍微写实,较长的中庭,略偏向中性向

2整体的元素尽量清晰准确,不要有太多乱七八糟的元素堆砌(目前还未完成)

3能够生成空白背景的人物立绘,也能生成带场景的成图

4比起追求一眼看过去的胡逼大概念,更在乎整体的合理性

这些需求决定了模型的长处和短板,也导致我从过去到现在发布的3个版本,可能在他人看来整体差别不大。

目前的版本还存在许多硬伤,如

1站着的人物比较容易画对,但一旦坐着腿就很容易画错

2对prompt的理解和忠实还原能力还是不太够,需要各式插件辅助

3虽然比过去的版本略好,但在不同的景别下,人脸的写实度还是会有差别,可能需要实时调整放大重绘的幅度,或使用face editor

希望对这个系列模型有兴趣的朋友可以多多尝试,如果能协助我解决这些问题,更将感激涕零。

以下机翻:

The original intention behind creating a customized model was to have an exclusive model that aligns with my personal vision of the "Project Shadow" art style.

 It is not primarily focused on achieving a universally optimal solution, but rather on fulfilling my specific requirements. Here are some aspects of the desired outcome:

1.Slightly more realistic than traditional two-dimensional art styles, featuring longer proportions and a slight inclination towards androgyny.

2.Overall elements should be as clear and precise as possible, avoiding excessive clutter (currently a work in progress).

3.The ability to generate character illustrations with blank backgrounds, as well as scenes with backgrounds.

4.Prioritizing overall coherence rather than pursuing flashy and abstract concepts.

These requirements determine the strengths and weaknesses of the model, and have resulted in the release of three versions that may not appear significantly different to others.

The current version still has several limitations, including:

1.Drawing standing characters is relatively easier, but there are challenges in accurately depicting characters in seated positions.

2.The understanding of and ability to faithfully reproduce prompts is still lacking, requiring the use of various plugins for assistance.

3.While the current version is slightly better than previous iterations, the level of realism in facial features may still vary across different backgrounds. Real-time adjustments in scaling, redrawing, or the use of a face editor may be necessary.

I hope that those interested in this series of models will give them a try. Any assistance in resolving these issues would be greatly appreciated.

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.