Creator:
 <a href="https://civitai.com/user/advokat" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/advokat
 </a>




 
 2DN-NAI v2.0 YANG
 


 Just as detailed as v2.0 YIN, but creamier, gentler and brighter. What I mean to say is: it's not as bonkers on contrast and SD1.5-like compositions, but it still packs a punch. For reference ALL of the preview images have the same settings, prompt and seed as the 阴versions, so you can compare them directly. And also, it's way way more creative as a model, expect surprises, pleasant ones! It also responds much better to LoRAs, meaning you can go ham with style and character models. It may seem a bit pale, but you can control this with various style LoRAs really well.

<hr/>

 For best results:


 
 Include in positive prompt:
 
 "masterpiece, best quality, amazing quality, very aesthetic, absurdres, very awa, .... "


 
 Include in negative prompt:
 
 "lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, 2koma, 4koma, comic, manga, text, logo, artist signature, patreon logo, patreon username, twitter username"


 
 Recommended settings:
 


 
 CFG:
 
 2 - 3


 
 Steps:
 
 14


 
 Sampler:
 
 Euler A

NAI-v2.0-YANG

Creator:
 <a href="https://civitai.com/user/advokat" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/advokat
 </a>




 
 2DN-NAI v2.0 YIN
 


 My best realistic model now goes a bit HARDER! See previous version for description. None of the preview images use ADetailer, the model does it's best to make details happen. Use minimal steps for reasonable results (higher step counts will produce high contrast). Overall, this model is: very fast, sharp and great for vibrant gens using NoobAI tags.


 Carried by an asian/anime aesthetic, it excels at NSFW gens - essentially stuff you can't get easily with ChatGPT/Gemini.

<hr/>

 For best results:


 
 Include in positive prompt:
 
 "masterpiece, best quality, amazing quality, very aesthetic, absurdres, very awa, .... "


 
 Include in negative prompt:
 
 "lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, 2koma, 4koma, comic, manga, text, logo, artist signature, patreon logo, patreon username, twitter username"


 
 Recommended settings:
 


 
 CFG:
 
 2 - 3


 
 Steps:
 
 14


 
 Sampler:
 
 Euler A

NAI-v2.0-YIN

Creator:
 <a href="https://civitai.com/user/advokat" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/advokat
 </a>




 
 2DN-NAI v1.0
 


 
 This is my best general-purpose model!
 
 All of the sample images have the same seed! They were not cherry picked!
 
 


 I wanted to make a model that leveraged the sheer creativity and knowledge of NoobAI (NAI) v-pred v1.0 - so after much "hitting head on brick wall" here it is!


 The culmination of all of the 2DN series model vision - a highly detailed model that lets you do anime, realism, slop, or fancy art, with the ability to produce striking images thanks to v-pred.


 For best results:


 
 Include in positive prompt:
 
 "masterpiece, best quality, amazing quality, very aesthetic, absurdres, very awa, .... "


 
 Include in negative prompt:
 
 "lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, 2koma, 4koma, comic, manga, text, logo, artist signature, patreon logo, patreon username, twitter username"


 
 Recommended settings:
 


 
 CFG:
 
 2 - 3


 
 Steps:
 
 14


 
 Sampler:
 
 DPM++ SDE


 
 Seed:
 
 3493447269

NAI-v1.0

Creator:
 <a href="https://civitai.com/user/advokat" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/advokat
 </a>




 
 2DN-LatentLens v1.0
 


 It uses the right sampler and scheduler settings not available on CivitAI or any other online image generator service. It is also very fast.


 Introducing
 
 2DN LatentLens
 
 .


 LatentLens is a v-pred model, based on NoobAI XL v-pred v1.0


 It uses a novel technique called LatentLens, which increases model responsiveness to prompts, coherence and quality. For example, most of the preview images use neither hires fix, face detailers nor upscaling. LatenLens makes models more flexible, allowing you to explore various creative prompting strategies while seeing consistently coherent and vibrant generation results.


 This model works with NoobAI artist tags (not pictured) and is good at explicit content (not pictured).


 My intention when working on this model was to "let people's dreams come true easily".


 For best results:


 
 Include in positive prompt:
 
 "masterpiece, best quality, amazing quality, very aesthetic, absurdres, very awa, .... "


 
 Include in negative prompt:
 
 "lowres, worst quality, low quality, bad anatomy, bad hands, multiple views, abstract, signature, furry, anthro, 2koma, 4koma, comic, manga, text, logo, artist signature, patreon logo, patreon username, twitter username"


 
 Recommended settings:
 


 
 CFG:
 
 2 - 3


 
 Steps:
 
 20


 
 Sampler:
 
 DPM++ SDE