Good to see you! Try the new model!
(6/18/2005)
Additional Information
Today, June 18, 2025, we released v2.1.1, an update to v2.1. This release stems from our passion as creators to deliver the best possible experience. However, if you are satisfied with v2.1, there is no need to download v2.1.1—it’s a matter of personal preference.
The updates address concerns about a slightly whitish, blurry atmospheric perspective, which we refined for clarity. Additionally, we enhanced color vibrancy and improved contrast to address the muted appearance in darker backgrounds.
Neither version is inherently better than the other. Please choose v2.1 or v2.1.1 based on your preference.
本日、2025年6月18日に、v2.1を改良したv2.1.1をリリースしました。このアップデートは、作り手としてより高品質なものをお届けしたいという強い想いから生まれました。もちろん、v2.1にご満足いただいている場合は、必ずしもv2.1.1をダウンロードする必要はありません。個々の好みによります。
修正内容として、全体的に白っぽくぼやけた空気遠近法が気になったため、これを調整しました。また、背景が暗い場合に発色がやや薄く感じられたため、色の鮮やかさを向上させ、コントラストも強化しました。
どちらのバージョンが優れているというわけではありません。お好みに応じて、v2.1またはv2.1.1をご利用ください。
And if you like it, please download it, write a review and press the Like icon. All of this will be my motivation.
LINK. TensorArt. yodayo. SeaArt. pixai, x.
(6/13/2005)
Announcement
With this version 2.1, coco-style-Illustrious-XL will no longer be updated.
And finally, we will complete all model updates with the release of two types of coco-style-NoobAI-XL - v8.0(v-pred/epsilon).
Thank you for your patronage.
coco-style-Illustrious-XL-v2.1
This version was developed based on version 2.0.
Changes from the previous version include reducing excessive style effects for a more user-friendly finish. The backlight has also been adjusted to achieve more natural dimming.
The biggest improvement is that it is now possible to generate higher resolution and higher detail, enabling stable rendering down to the fingertips. It offers greater stability than cocostyle-Noob-XL-v6.0 in details such as fingertips.
The resolution remains unchanged from v2.0, with standard support for 1536×1536.
Sample Image Description
Many sample images were generated using high-res (1.5x upscale), ADetailer, and CD Tuner. Of course, high-quality illustrations can be created without these tools.
Additionally, the model supports a wide range of LoRA, character tags, and artist tags.
When using character tags, adding “anime style” to the quality tag will reduce realism. If you want to reduce it further, add ‘3D’ and “2D” to the negative prompt.
日本語説明はバージョン情報を読んでください
今回のバージョン2.1をもってcoco-style-Illustrious-XLは更新を終えます。
長らくのご愛顧ありがとうございました。
Please refer to the version information below.
(6/1/2005)
coco-style-Illustrious-XL-v2.0
The base model is Illumium XL (Illustrious) v3.1 (e-perd). I looked for a model that would encompass the new dataset.
I merged my unpublished model (created on IllustriousXL-2.0 base) and style LoRA (2D and illustration types) into this model.
Therefore, when generating images with a resolution of 1536x1536, the model is stable
Also, due to the influence of my style LoRA and the LoRA described below, there is more interpretation of the prompts than in the previous v1.0 model, allowing for freer illustrations and improved color representation.
We have achieved a high quality fusion of realism and illustration, one of our efforts since last year.
Please enjoy the various expressions from extraordinary fantasy scenes to everyday scenes.
Some of the sample images use Hires x 1.5 and ADetailer.
If you have not yet added ADetailer to your extension, clicking on ADetailer will lead you to the creator's github and cloning the repository will install it.
My advice in using this model is that you do not need a LoRA with a strong style system of change. It is already moderately merged. Flavored.
Also, since many of my sample images are high resolution, the clarity may be impaired depending on the monitor you are using. This seems to be a problem on the civita side. If this is the case, please try viewing the images on your smartphone or other device.
Disclaimer
(This model is not intended to generate explicitly obscene expressions. However, there is a possibility that it may be generated unintentionally. SFW and NSFW decisions are made on an individual basis and are not intended to restrict the tastes and preferences of individual users.)
My request to you all.
Please share the merge recipe if you wish to publish the merged model with coco-style-Illustrious-XL.
List of Lora used for merging according to Fair AI Public License 1.0-SD
Specification tool kohya-ss-gui
Merge Ratio
Genesis_mk0.4: 0.3
Detail Tweaker XL: 0.7
Aesthetic Quality Modifier(Illustrious): 0.7
coco-style-Illustrious-XL-style-LoRA:0.3
coco-style-Illustrious-XL-3DLoRA:0.3
The following terms and conditions must be complied with
The main contents of the Fair AI Public License 1.0-SD are as follows
Permission AI models may be used for both commercial and non-commercial purposes.
Modification and Redistribution: Modification and redistribution are permitted, but require the continued application of the same license. (This includes the prohibition of commercial use, distribution, or sale of models identified and integrated by the provider.)
Limitation of Liability: Licensor is not liable for any damages arising from the use of the models.
Transparency: Disclosure of model training data and training methods is encouraged.
Ethical Compliance: Discriminatory or harmful uses are prohibited.
Respect and thanks to duongve13112002, the creator of Illumium XL (Illustrious) v3.1 (e-perd), for making it available to the public!
How to use this model well
Euler a SGM Uniform /Euler Ancestral CFG++Bet//CFG scale4.5-5.5 / step15-30 / 720x1280 /768x1344, 896×1536, 1080×1920 /clip skip2.
prompts
masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, newest, 2023, 2024, HDR, 8K, high detailed, Additional Prompts
subtle light, high contrast, detailed background, color depth, chiaroscuro, impasto, smooth shading, glossy surfaces, shiny skin,Also recommended
dak depth, low kye, intricate details, masterful shading, detailed background, chromatic aberration, cinematic composition, blurry foreground, blurry background, moody atmosphere, muted colors, etc.Negative prompts
lowres, worst quality, bad quality, bad anatomy, jpeg artifacts, bad finger, missing finger, watermark, artistic error, signature, artist name, displeasing, worst aesthetic, old, early, simple eyes, simple shading, simple drawing, simple face, simple coloring, mismatched pupils, logo, The model may have a taste similar to 2.5 as a feature of the model. In that case, please add 3d, realistic, etc. to the anime style or negative prompt.
To prevent unauthorized reproduction and for the benefit of those who wish to build LoRAs, we will be publishing models on other sites in the future. Reproduction of my models on websites by anyone other than myself is prohibited, even if it is not for profit. The sale of any products is prohibited. (01/21/2025)
Illustrious XLのライセンスセクションをご覧ください。
License：Fair AI Public License 1.0-SD
Description
モデルに関する詳細やライセンス等の概要はv.2.0のバージョン情報をご覧ください。
このバージョンはv.2.0をベースに再調整されました。
ｖ2.1からの変更点としては、過度なスタイルエフェクトを削減し、よりユーザーフレンドリーな仕上がりを実現しました。また、バックライトの調整により、より自然な調光を実現しました。
最大の改良点は、より高解像度・高精細な描画が可能になり、指先まで安定したレンダリングが可能になったことです。指先などのディテール表現において、cocostyle-Noob-XL-v6.0よりも高い安定性を実現しています。
解像度はv2.0から変更されておらず、1536×1536が標準でサポートされます。。
多くのサンプル画像は、high-res (1.5x upscale)、ADetailer、CD Tunerを使用して生成されています。もちろん、これらのツールを使用しなくても、高品質なイラストを生成できます。
また、多数のLoRA、キャラクタータグ、アーティストタグに対応しています。
お知らせ
このバージョン2.1を最後に、coco-style-Illustrious-XLのアップデートは終了いたします。
また、coco-style-NoobAI-XLの2種類（v8.0（v-pred/epsilon））のリリースにより、すべてのモデルアップデートを完了いたします。
ご支援いただき、誠にありがとうございました。
FAQ
Comments (12)
2.1 is straight up broken on webui reforge. This is what I get when I try to recreate OP main picture: https://files.catbox.moe/jw77tc.png
Nevermind, I re-downloaded it and it works perfectly. Great mix! :D
I fell in love with the BETA version and this new 2.1 version now looks generic, its so glossy for me. I posted an example comparing both side to side
Very good model, this is the model I use most recently, please keep up the good work, creator!
the colors and details are crazy
Please refrain from posting NSFW content. Also, while swimsuits and other revealing clothing are acceptable, please refrain from posting overly explicit images.
I'm not seeking pornography. Today, Stability AI added a policy prohibiting the generation of sexual or pornographic content. This is my response. It's about time Civitai stops being a porn site and focuses on increasing its corporate value. Flux also prohibits sexual content. This trend should not be ignored.
Announcement
I shared my thoughts on the page of my publicly shared model, only to be met with criticism and mockery from certain users—those seen as respected citizens and guardians on Civitai. Deeply disappointed by this, I’ve decided to delete all my models by the end of this month. I’ve already taken down all models except v2.1, which I’ll leave up for now as a grace period. The increasing lack of courtesy and ethics on Civitai has also played a big part in this decision. About a year ago, I started contributing to Civitai with the hope of helping it grow. I feel I’ve more than fulfilled that goal.
I had planned to release coco-style-Noobxl-v8.0 (vpred), which took a month to create, as early as next week, but it’s unfortunate that it won’t happen.
THAT FK, WHY YOU DISAPPEAR, Glad i have some back up of your Model but Helll no, dont let the FKER WIN man.
You better than them
Fk sake.
This is why what your model, merge with a other help me to achieve. Honestly, im sad you will maybe quit one day civit but thank for everything and i wish better luck whatever platefor you use.
https://civitai.com/posts/18479034
https://civitai.com/posts/19651344
https://civitai.com/posts/19651391
Please continue to update, the model is too good.
No better than xitter artists throwing a fit and deleting their accounts. It's cool, these are all in the archive anyway. Thanks for your work
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.