Img2img+face detailer workflow(Flux/Illustrious),and you can compare the result before/after the face refine.<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">I tested with several checkpoints,this workflow fits better with:<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">For flux dev version: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1090420/edge-of-reality?modelVersionId=1677057">Edge of Reality 真实边缘 - 3.2 Beyond Reality | Flux Checkpoint | Civitai</a>For illustrious version:<a target="_blank" rel="ugc" href="https://civarchive.com/models/974015?modelVersionId=1161771">Vauxz Merge 2.5D - 3D - ILLU v.Sarah | Illustrious Checkpoint | Civitai</a>

Files with SHA256: 6d6e41367a7fec720b0f54a05b03bca0f37face6e8c5cf66c51cf899eff72200