Use <a target="_blank" rel="ugc" href="https://civarchive.com/models/15003?modelVersionId=138176">CyberRealistic </a><a rel="ugc" href="https://civarchive.com/models/25694?modelVersionId=134065">epiCRealism</a> <a rel="ugc" href="https://civarchive.com/models/4201?modelVersionId=130072">Realistic Vision</a> for better result<ul><li>Use simple prompts. Complex prompts might make less realistic pictures because of CLIP bleeding. More complex prompts does not mean better results. Keep it simple.</li><li>Use <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">ADetailer</a> to enhance faces. Basically every solo portrait I made uses it. You can get my settings by clicking on "copy generation data". I suggest you use denoising under 0.3 to avoid getting always the same face.</li><li>Use BadDream and UnrealisticDream negative embeddings (<code>BadDream, (UnrealisticDream:1.2)</code>). Add weight to UnrealisticDream between 1.2 and 1.5. Do not use FastNegative or EasyNegative if you aim at realism. However, they're good for artworks.</li><li>Use Highres.fix with the following settings: <code>Denoising strength: 0.45, Hires steps: 20, Hires upscaler: 8x_NMKD-Superscale_150000_G</code> and as much upscale as you can (my gpu only handles up to x1.8 at 512x768 base resolution, but you can go higher). If you don't have <code>8x_NMKD-Superscale_150000_G</code> you can probably use another GAN, but it should be easy to find on Google. You can also try Latent with a denoise higher than 0.6, but the result will be harder to control.</li><li>Try to condition faces by prompting for eye colors, hairstyles, hair color, ethnicity and so on. Even celebrity names do work. This model is pretty good at not making a single face if you play with the context.</li><li>If the pic is too clean, try to add some ISO noise. Even as a post processing with external tools it will trick the brain enough to make you think "damn, this is a real photo.</li><li>If you feel the grounded nature of this model is limiting your imagination, try generating on DS6 and then do img2img with this one to bump up the realism.</li></ul>

Files with SHA256: aae2594b3f234466b8306644947437ee54dd015c457be892d3aac24fd8ea7815