Next version of photorealistic merge. This version experiments on PAG node in ComfyUI. Inspired by Enzino and other fantastic SDXL model creators. The brightness level is slightly lowered for cinematic effect. This is a NSFW merge - so use it with discretion.


 Model by
 <a href="https://civitai.com/user/zepled23" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/zepled23
 </a>

A new merge, this time by using Perturbed Attention Guidance. (
 <a href="https://github.com/cvlab-kaist/Perturbed-Attention-Guidance" rel="noopener noreferrer nofollow" target="_blank">
 https://github.com/cvlab-kaist/Perturbed-Attention-Guidance
 </a>
 ). I have added a DMD2 checkpoint with very little weight to get amazing results but this is NT a DMD2 model.


 Prompt: RAW portrait Photo of a woman, semi-side view, looking at viewer, wearing a maroon sweater, dark Paris sidewalk background, night, bokeh


 Steps: 30, Sampler: DPM2 a, Schedule type: SGM Uniform, CFG scale: 5, Model: ZEP11, VAE hash: a30a98f479, VAE: sharpnessAndContrast_v10.safetensors, Version: v1.10.1


 The model does not render few art styles like Zep9 but has a new look especially for people related prompts. This model can do NSFW and need users to use prompts and negative prompts to get SFW content. Enjoy!


 Model by
 <a href="https://civitai.com/user/zepled23" rel="noopener noreferrer nofollow" target="_blank">
 https://civitai.com/user/zepled23
 </a>

The next checkpoint in the series! This includes Select LoRAs in the merge. Enjoy!


 Moedel by
 <a href="https://www.seaart.ai/user/a6bd3d749cd454130dd50d0d5ceb7505" rel="nofollow" target="_blank">
 
 zepled23
 
 </a>