<h1 id="heading-10">VividPDXL Real (Near photorealism)</h1><h3 id="heading-32">Why use this? It has decent color, skin texture and eye quality for a pony model, and can achieve photorealism.</h3><h3 id="heading-4">NO UNNECESSARILY LONG NEGATIVE PROMPTS, MOST OF THE TIME THEY HURT RATHER THAN HELP!!!</h3><ul><li>My usual visual tags are volumetric lighting, depth of field, cinematic, vibrant, shadows, detailed but these may force realistic images even if you are trying to do a different style.</li><li>Use source_photo and Realistic tags to help get realistic images.</li><li>Make sure to keep CFG around 7 and Sampling Steps around 30.</li><li>Always use score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up you can remove the 4,5 and 6 one and you likely wont have any issues.<pre><code>score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, just describe what you want, tag1, tag2</code></pre></li><li>Recommended Negatives: artist name, signature, only add more if you want to avoid things appearing in your generation like styles or objects/people. You don't need to use tons of random negatives like deformed fingers I highly doubt they work.</li><li>Use source_anime, source_photo, source_3d, etc.. to force or avoid certain styles. You won't see the style change that much but it can help.</li><li>If you really want styles other than photorealism, you can try, but its not guaranteed. Try using words like style of "stylehere", while putting source_photo, realistic in the negative prompt as well as describing elements of that style. Certain visual positive prompts can also force a realistic style as well, so try experimenting.<ul><li>If you go through the gallery below and look at badassdragoon2's images, you may find some examples of different styles you can use. <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343039">Set 1</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343037">Set 2</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343046">Set 3</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343043">Set 4</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343040">Set 5</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343032">Set 6</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2343029">Set 7</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2393986">Set 8</a>, and <a target="_blank" rel="ugc" href="https://civarchive.com/posts/2393988">Set 9.</a></li></ul></li></ul>Check out <a target="_blank" rel="ugc" href="https://github.com/DominikDoom/a1111-sd-webui-tagcomplete">this extension(tagcomplete)</a> for automatic111 users to help with finding tags for pony models.Also use <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/">danbooru</a> to help find tags, it has a tag count to show you how popular certain tags are.<h1 id="heading-257">VividPDXL V1.1 (2.5d realistic style)</h1><h3 id="heading-32">Why use this? This version produces a more 2.5d like style compared to REAL.</h3>A slight update over 1.0 improving color slightly, and detail.<h2 id="heading-200">My usual settings for pony models are as follows:</h2>Res: 1024x1024Sampler: DPM++ 2M Karras (DPM++SDE Karras, DPM++ 3M SDE Karras are all excellent as well)<ul><li>Euler for lower detail images.</li></ul>Steps: 30CFG: 7Hires Denoising: .3 - .4<h3 id="heading-12"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/644ef861-a095-4648-aa38-2b54e65936cf/width=525/644ef861-a095-4648-aa38-2b54e65936cf.jpeg" /></h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/28a1a4ac-b050-4e63-b997-858156abc586/width=525/28a1a4ac-b050-4e63-b997-858156abc586.jpeg" /><h3 id="heading-190"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e14b0569-f2ad-49a4-90bc-d2a916078b3a/width=525/e14b0569-f2ad-49a4-90bc-d2a916078b3a.jpeg" />REAL</h3><h3 id="heading-191">This update can create photorealistic images, but can sometimes creates a 3d look depending on prompts and loras.</h3><h3 id="heading-811">V1.1</h3><h3 id="heading-812">Slightly improved color/contrast, maybe a slight improvement to detail and merged the sdxl_vae.</h3><h3 id="heading-813">V1.0</h3>Troubleshooting:If you see a faded image with white spots you need to download sdxl_vae and place it in your models/vae folder.<h3 id="heading-192">REAL is a merge of a high contrast 1.1 and <a target="_blank" rel="ugc" href="https://civarchive.com/models/405136?modelVersionId=451700">Zonkey</a></h3><h3 id="heading-15">V1.1 is a merge of...</h3><a target="_blank" rel="ugc" href="https://civarchive.com/models/314840?modelVersionId=353166">MFCG PDXL</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/341433?modelVersionId=399640">Everclear PNY by Zovya</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/257749/pony-diffusion-v6-xl">PonyXL</a>My Model <a target="_blank" rel="ugc" href="https://civarchive.com/models/366162/vividvisions?modelVersionId=409170">Vividvisions</a><ul><li>Which is a merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/351305?modelVersionId=392988">Duchaiten-NijiUncen v1Lightning</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005/juggernaut-xl">JuggernautXL V9RDPhotoLightning</a></li></ul>

VividPDXL

Improved color/contrast slightly and added a VAE to the merge. It might also add more details to an image but I'll need to test more to verify.

Files with SHA256: 92ff165c2e0ff1a8c641e15e57eeb8872375cbb2b3022e36de60e6564d1204a1