NanoBanana Lite Image To Image is now on ModelsLab

Try Now
Skip to main content

Stable Diffusion

Night Sky Yozora Style Model

model_id: night-sky-yozora-sty

<h1><strong>Night Sky YOZORA Model &mdash;&mdash;&ldquo;For ultimate image quality and large image size(&gt;1536 x 1024)&rdquo;</strong></h1> <h3><strong>Trained by&nbsp;<a href="https://civitai.com/user/YozoRaAru">@YozoRaAru</a></strong></h3> <h2><strong><em><u>如果你需要更好的色彩表现,我推荐你试一下</u></em></strong><a href="https://civitai.com/models/21200/color-box-model" target="_blank" rel="noopener ugc"><strong><em><u>Color Box</u></em></strong></a></h2> <h2><strong><em><u>If you want better colour representation There is a new style model&nbsp;</u></em></strong><a href="https://civitai.com/models/21200/color-box-model" target="_blank" rel="noopener ugc"><strong><em><u>Color Box</u></em></strong></a></h2> <p><strong>YOZORA</strong>&nbsp;is a model that pursues perfection and is&nbsp;<strong>filled with personal preferences</strong>. I trained it using images that I like, which give it an unparalleled level of detail and completion. It can provide you with very exquisite character images.</p> <p>In addition to training, I also blended it with dozens of other high-quality models that I personally like, and I tried layer blending as well. Among these models, I selected NovelAI's original model as the major weight because it can give it excellent adaptability to a variety of prompts. I haven't tried testing it with landscape + character yet, but I believe it can also perform excellently in that aspect.</p> <ul> <li> <p>For the&nbsp;<strong><em>best results</em></strong>, please ensure that your&nbsp;<strong><em>final resolution &gt; 1536x1024</em></strong>. This is&nbsp;<strong><em>necessary</em></strong>&nbsp;for generating exquisite illustrations</p> <p>&nbsp;</p> </li> </ul> <p>Here are some recommended settings for the parameters:</p> <ul> <li> <p><strong>Clip skip</strong>: It is recommended to set it at no less than 2.&nbsp;<strong>YOZORA</strong>&nbsp;already has a rich level of detail, and setting it at 1 may make the image appear cluttered and confusing.</p> </li> <li> <p><strong>Resolution</strong>:&nbsp;<strong>YOZORA</strong>&nbsp;may&nbsp;<strong>not be suitable for generating small images</strong>&nbsp;because the extreme level of detail may become too crowded. It is recommended&nbsp;<strong>do not use Hires.fix</strong>&nbsp;to generate&nbsp;<strong>large images</strong>. A larger resolution is equivalent to a larger canvas, making it easier for YOZORA to capture details. It is recommended to use&nbsp;<strong>1536 x 1024</strong>&nbsp;or higher for Hires.fix.</p> </li> <li> <p><strong>Negative prompts</strong>: It is recommended to use&nbsp;<strong>EasyNegative</strong>&nbsp;to provide brief and precise descriptions.</p> </li> </ul> <p>The name YOZORA means&nbsp;<strong>"strolling among the stars in the night sky"</strong>. I hope that she can bring you the excitement and joy of a sky full of stars on a starry night.</p>

NSFW samples are gated

This model produces NSFW content. Log in and enable NSFW in your account settings to view samples and run the model. The API and model parameters below are accessible regardless.

Use Night Sky Yozora Style Model via the ModelsLab API

Send a POST request to the relevant endpoint with your API key and model_id="night-sky-yozora-sty". The API does not enforce the same NSFW gating as the web playground — content moderation is handled by your account-level policy. Sign up to get an API key.