BrightProtoNuke(BPN) - No refiner needed

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




 
 
 Easy image quality, more creative output
 
 




 
 V1.3 Update (creativity upgrade)
 


 Merged in the amazing
 <a href="https://civitai.com/models/218300/paradox-2-sd-xl-10" rel="ugc" target="_blank">
 Paradox2
 </a>
 model for it's creativity. Managed to keep the BPN1.2 hands intact(mostly). How far can you push the model before it stops to really understand what you want?


 All preview images are pure txt2img, no lora's used.

<ul>
 <li>
 
 A lot more creative imagery
 
 </li>
 <li>
 
 Listens to prompt a lot better (some prompts won't work anymore because it might listen too well)
 
 </li>
 <li>
 
 Has some repetitivity issues when it comes to buildings in wide shots (1280+px width, to be fixed in future merge)
 
 </li>
 <li>
 
 Less character, more creative focused
 
 </li>
</ul>

 Because the model is a lot more creative now, sampler choice becomes more a factor too. Use DPM++ type samplers if you want cartoony styles, or Euler/Heun type (which includes Restart) samplers for photorealistic. If consistency is what you want, i advice to use LCM. FreeU and SAG were used for images, but they add little/no extra generation time.