<h3>Built with the concept “Prompt less, Post more”</h3>Just only short prompt and you will get a realistic portrait photo. Let you focus on posting on social media, building engagement, and doing other things that are important to you.*** This Model needs VAE !!! ***<h3>Overview:</h3><ul><li>The purpose of this model is to generate a portrait photo.</li><li>These models require a VAE. You can try mse-840000-ema or anything. I have a photo of the comparison in the Comparison section (below)<ul><li>If you got bugs, adding '--no-half-vae' to the argument will solve it.</li></ul></li></ul><h3>Recommends:</h3><ul><li>Prompt:Try to start with<code>(skindentation:1.2), (realistic:1.1), best quality, photorealistic,</code> + your prompt (eg. 1 girl, wearing a white shirt)Negative: <code>lowres, normal quality, ((monochrome)), ((grayscale)), BadHand v4</code></li><li>Steps: I recommend 30-45 (You can use higher, but many times do not have a big difference)</li><li>Sampling Methods: You can see the comparison in the Comparison section (below).</li><li>Sizes:Medium shot: 512x512, 512x768, 512x904Long shot (full body): 768x1152, 768x1356Can be used both vertically and horizontally</li><li>Hires. fix: Use Denoising strength less than 0.6 (but you can try &gt;= 0.7, sometimes you will get problems with the hands)</li></ul><h3>Comparison:</h3># VAE<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a413c594-0262-4f2a-acdc-afc9f28d5884/width=525/a413c594-0262-4f2a-acdc-afc9f28d5884.jpeg" /><a target="_blank" rel="ugc" href="https://github.com/Jirayu-ninl/SD-IceJi-ProPortrait/blob/main/vae-xyz_grid-0000-3322330494.png?raw=true">full-size image</a># Steps<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/14a700c7-a4a8-494f-b801-861d230aae66/width=525/14a700c7-a4a8-494f-b801-861d230aae66.jpeg" /><a target="_blank" rel="ugc" href="https://github.com/Jirayu-ninl/SD-IceJi-ProPortrait/blob/main/steps-xyz_grid-0000-349146491.png?raw=true">full-size image</a># Sampling Methods (with steps 45)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5b4f40e4-f6c1-4637-bac3-24a5a4655a27/width=525/5b4f40e4-f6c1-4637-bac3-24a5a4655a27.jpeg" /><a target="_blank" rel="ugc" href="https://github.com/Jirayu-ninl/SD-IceJi-ProPortrait/blob/main/samplers-xyz_grid-0000-349146491-min.png?raw=true">full-size image</a><h3>Ingredients:</h3><ul><li>ProFantasy II C-Base Model (<a target="_blank" rel="ugc" href="https://civarchive.com/models/52298">ProFantasy</a>)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/25494/">BRA</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/9052">LOFI</a></li><li>Portrait Photo Training Checkpoint (by <a target="_blank" rel="ugc" href="https://civarchive.com/user/DimensionsAI">DimensionsAI</a>)</li></ul>(Merge with U-Net weight-block technique)<h3>Disclaimers:</h3><ul><li>Do not sell: on any website.</li><li>Credit: If you use my model in your own merges</li><li>Not authorized: to be used on generative services (without my permission)</li></ul>

Files with SHA256: 4ecccf625ca1cad157fb83af4880098ce1aa032f6466e2f543bd9d2670347908