A dark fantasy sorceress elf with long dark green hair and blue eyes sits on an ornate golden throne holding a white staff. She wears a red cloak with gold-trimmed garments, white gloves, and a golden headdress. Her scarred thigh is visible, with two glowing red demon faces looming behind her.
A cyberpunk boy with spiked dark blue hair, yellow t-shirt, and mechanical arm stands in a neon-lit alley holding blue katanas, wearing aviator sunglasses and cargo pants.
A blonde-haired monk girl standing on snow-covered tree stumps in a forest, holding a log on her shoulder in a dynamic pose with emerald eyes and a kesa robe.
Girl with short pink hair and purple sailor school uniform sitting on a wall beneath cherry blossom trees with petals falling, grayscale city background.
Photorealistic portrait of a blonde woman with long wavy hair and striking green eyes, wearing vibrant colorful jewelry and accessories against a bright multicolored abstract background.

Empfohlene Prompts

masterpiece, best quality, amazing quality, very awa, absurdres, newest, very aesthetic, depth of field, highres

solo, 1girl, masterpiece, best quality, very awa, absurdres, amazing quality, newest, very aesthetic

Empfohlene Negative Prompts

worst quality, normal quality, anatomical nonsense, bad anatomy, interlocked fingers, extra fingers, watermark, simple background, transparent, low quality, logo, text, signature, face backlighting

( badly drawn hands and fingers, anatomically incorrect hands), multiple views, jpeg artifacts, patreon logo, patreon username, web address, artist name, safe_neg, unfinished, displeasing, worst quality, oldest, normal quality, early, anatomical nonsense, artistic error, scan, interlocked fingers, bad anatomy, extra fingers, watermark, simple background, transparent, low quality, text, logo, signature

Empfohlene Parameter

samplers

Euler a, Euler, DPM++ 3M SDE

steps

25 - 35

cfg

2 - 6

resolution

768x1344, 832x1216, 896x1152, 1216x832, 1344x768, 1536x640, 640x1536, 1536x1536, 1728x1344, 1344x1728, 1824x1248, 1248x1824, 2016x1152, 1152x2016, 832x1216

Empfohlene Hires (Hochauflösungs-) Parameter

upscaler

R-ESRGAN 4x+ Anime6B

upscale

1.5

denoising strength

0.7

Tipps

Add lighting tags like (profile light, contour light) to enhance lighting effects.

Add (dark, chiaroscuro, high-contrast:1.7) to make the image darker.

Use ((realistic, photorealistic, realistic shading)) for semi-realistic characters.

Add (anime screenshot) and (anime coloring) to replicate anime style.

Add (photorealistic, realistic, 3d, photography) to negative prompts to avoid 2.5D semi-realistic style.

Use ADetailer (https://github.com/Bing-su/adetailer) to enhance facial details.

Explore artist collaborations through tags hidden in prompts.

The sample images have no LORA applied, explore adding other enhancements on your own.

Versions-Highlights

1.2版本:我们的口号是不加Lora也很好看!Euler画风偏漫画一些,Euler a画风整洁一些。建议CFG3-5低一些,我喜欢CFG4,20-30steps,不过用绘画标签依然能展现2D效果。偏写实了一点点,还原各个年龄的角色,极致光影回归,增强更华丽背景,人物再次增强质感强化了2.5D,强化肢体动作,眼睛更迷人,增加了可爱的数据集。

Version 1.2: Our slogan is that it looks great even without Lora! Euler's art style is more like a comic, while Euler a's art style is more neat. We recommend setting CFG3-5 lower, I prefer CFG4, 20-30 steps. However, using painting labels can still show the 2D effect. It's a bit more realistic, restoring characters of various ages, and returning to the extreme light and shadow. The background is more gorgeous, and the characters are once again enhanced in texture, strengthening 2.5D, and enhancing the body movements. The eyes are more charming, and a cute dataset that is more adorable has been added.

Ersteller-Sponsoren

If you like my work, please give me a good review and click the thumbs-up icon. Please give me more feedback! It's free, and it can keep me motivated to create.

如果你喜欢我的作品,请给我一个好评并点击大拇指图标。多多返图!这是免费的,而且能让我保持创作动力。

AI绘画QQ交流群:4654350 Discord:https://discord.gg/7RNWedD59H

推荐一个forge或webui的插件,方便 Illustrious的动漫角色的选择,插件可以扩展URL安装,插件链接如下:https://github.com/lanner0403/WAI-NSFW-illustrious-character-select

If you like my work, please give me a good review and click the thumbs-up icon. Please give me more feedback! It's free, and it can keep me motivated to create.

如果你喜欢我的作品,请给我一个好评并点击大拇指图标。多多返图!这是免费的,而且能让我保持创作动力。

Still, I repeat, the new version may not necessarily be the best. Experience it yourself and have fun!

^^!绘画标签都藏在图片提示词中!寻找画师串也是乐趣所在!例图未加任何lora,其他自己探索吧!还是那句话,各有特色新版本不一定是最好的。自己体验,玩得开心AI绘画QQ交流群:4654350 Discord:https://discord.gg/7RNWedD59H

^^! The painting tags are all hidden in the picture hints! Finding artists to collaborate with is also a lot of fun! The example picture hasn't been enhanced with any lora, and the rest is up to you to explore! As I've said before, the new version may not be the best. Experience it yourself and have fun! Discord:https://discord.gg/7RNWedD59H

推荐一个forge或webui的插件,方便 Illustrious的动漫角色的选择,插件可以扩展URL安装,插件链接如下:https://github.com/lanner0403/WAI-NSFW-illustrious-character-select

可盐可甜可干爽可油腻可3D可2D 可涩涩可清纯 打造泛用性最强二次元Illustrious微调大模型!(狗头)

光影方面建议加:(profile light,contour light), 等来强化光影

如果希望画面变暗可加: (dark,chiaroscuro,hight-contrast:1.7),

人物半写实可加:((realistic, photorealistic, realistic shading)),

还原动漫可以加:(anime screenshot),动漫截图,(anime coloring ),动漫上色,来还原

不喜欢2.5D半写实画风的负面加:(photorealistic, realistic, 3d, photography),

The thief website [PixAI] has illegally used my model without my permission. Moreover, my model is free and has been published on...

小偷网站[PixAI],未得到我的许可,非法使用我的模型。而且我的模型是免费的,发布在

https://civitai.com/models/1318945/one-obsession

https://civitai.com/models/1368727/one-obsession-branchmaturenoobaivpred

★NOW★

1.4,这个版本变化有点大,默认是2.5D的人物,(可以通过画风标签的tag改变)比上个版本加强了一点3D,画面整体干净,质感不错,其他轻微调整。

1.4 This version has quite a lot of changes. The default characters are 2.5D, (which can be changed through the tag of the art style) and it has been slightly enhanced in 3D compared to the previous version. The overall image is clean, and the texture is quite good. There are other minor adjustments.

You can use ADetailer to enhance facial details:https://github.com/Bing-su/adetailer

可以使用 ADetailer 来增强面部细节:https://github.com/Bing-su/adetailer

推荐我喜欢的分辨率:768X1344 832X1216

Model Recommended Resolution:768X1344 832X1216

Illustrious 1.0(noobAI):896 x 1152、1216 x 832、832 x 1216、1344 x 768、768 x 1344、1536 x 640、640 x 1536,

Illustrious 2.0{Rouwei Illustrious1.1}支持更大分辨率:1536x1536、1728x1344、1344x1728、1824x1248、1248x1824、2016x1152、1152x2016

正面词 Positive Prompt:

masterpiece, best quality, amazing quality, very awa,absurdres,newest,very aesthetic,depth of field, highres,

反义词 Negative Prompt:

worst quality,normal quality,anatomical nonsense,bad anatomy,interlocked fingers,extra fingers,watermark,simple background,transparent,low quality,logo,text,signature,face backlighting,

Recommended settings:

Steps: 25-35

CFG scale: 3-6

Sampler: Euler a Euler

Mitwirkende

Zurück
Hyper Detailed Illustration - v1.0
Weiter
Flux chaotic expressive lineart - v1.0

Modell-Details

Modelltyp

Checkpoint

Basismodell

Illustrious

Modellversion

1.2 2.3D Details+

Modell-Hash

b90f566024

Ersteller

Diskussion

Bitte log in um einen Kommentar zu hinterlassen.

Bilder von One obsession - 1.2 2.3D Details+

Bilder mit anime

Bilder mit basismodell

Bilder mit one

Bilder mit sexy