NatViS: Natural Vision

Creator:
 <a href="https://civitai.com/user/ndimensional">
 https://civitai.com/user/ndimensional
 </a>


 About this version
8step Hyper Varient of v2.7 with consistent CFG
(Meaning you can use the same CFG as the base v2.7 model)


 Generation Parameters:
Steps: 7 - 9 (Recommended 8)
CFG: 6 - 8 (Recommended 7)
Sampler: Euler

v2.7_Hyper_8step_CFG

Creator:
 <a href="https://civitai.com/user/ndimensional">
 https://civitai.com/user/ndimensional
 </a>


 NatViS (Natural Vision) is a photorealistic full-parameter fine-tune of SDXL that uses Natural Language prompting to generate high quality SFW/NSFW images. Trained on 1M+ image-caption pairs on a dataset that’s been expanded and refined for over a year.


 Changelog
11-18-24 NatViS v2.7


 Due to time constraints, pre-release changelog can be viewed at
 <a href="https://ko-fi.com/post/NatViS-v2-7-U7U015FWEN">
 https://ko-fi.com/post/NatViS-v2-7-U7U015FWEN
 </a>


 Note: I was bored generating the same sample images over-and-over again and decided to spice things up with some new prompts. Prompts from previous versions will work with v2.7. When I have time, I'll upload a separate gallery for images generated with the old prompts.

v2.7

NatViS (Natural Vision) is a photorealistic full-parameter fine-tune of SDXL that uses Natural Language prompting to generate high quality SFW/NSFW images. Trained on 1M+ image-caption pairs on a dataset that’s been expanded and refined for over a year.
Note: NatViS is still being trained. V1 (epoch 68) wrapped up training on July 19th, 2024.

<hr/>

 9-25-24 NatViS v2.0


 What's New?

<ul>
 <li>
 
 Prompting: This update focuses primarily on the text-encoders. Natural language prompting capabilities have been improved to follow less-strict formats and relies less on using specific tokens.
 
 </li>
 <li>
 
 Ethnicity and Demonym: Increased accuracy of phenotypes for various ethnicities and demonyms. Not just limited to body structure, but also includes clothing, hair, landscapes, ect.. See here for small examples.
 
 </li>
 <li>
 
 Camera EXIF: Inclusion of Camera EXIF data for popular modern and analog cameras that can be prompted. Includes, Camera Name, Focal Length, f-stop, ISO, shutter speed, lens type. Also includes attachments such as ND filters, polarizers.
 
 </li>
 <li>
 
 Analog: Improvements to analog and vintage photograph generations.
 
 </li>
 <li>
 
 Lighting and shadow: Prompt how light (or thereof) interacts with objects/subjects in the scene. Amongst other general lighting related modifiers. More info soon.
 
 </li>
 <li>
 
 Skin Textures: Small improvements to the detail of skin textures with less or no explicit token related to skin detail.
 
 </li>
 <li>
 
 Implementation of Pseudo Instruction: This will require a more lengthy write-up.
 
 </li>
 <li>
 
 Better male anatomy.
 
 </li>
 <li>
 
 Lesbians.
 
 </li>
</ul>