Reality Bound XL

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




 
 About this version
 


 This is basically a re-upload of v7.0 fp16, but the internal clip encoders have been replaced with:


 
 LongCLIP Distilled
 
 
 fp32 Clip L &amp; Clip G pre-trained
 


 The new clips have better training.


 
 Details
 
 :

<ul>
 <li>
 
 Adds more overall image detail
 
 </li>
 <li>
 
 Better prompt adherence
 
 </li>
 <li>
 
 A lot more accurate when tokenizing prompts
 
 </li>
 <li>
 
 Better prompt refining based on context
 
 </li>
 <li>
 
 Just better gens, period
 
 </li>
</ul>

 Base model is the fp16 precision version. The bigger size is because LongCLIP G is 2.8 GB, and the original clip is 1.6 GB.


 
 
 Felldude Links:
 
 


 Long Clip:


 <a href="https://civitai.com/models/1805024/long-clip-distilled" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/models/1805024/long-clip-distilled
 </a>




 This series is focused on women and the female body, in every kind of setting or style. It can do fine art, social media style, surrealism, cinematic, and pornographic very well. The main goal is to have as much diversity as possible in an SDXL checkpoint. Diversity in ethnicity, body type, faces, posing, personality, and locations.




 The VAE is baked in. No loras were used for the sample images.