If you want to learn how to train faces with high fidelity, reach out to me on my <a target="_blank" rel="ugc" href="https://www.patreon.com/sdisn">Patreon</a>. :)<h3 id="about:-kt2t4u6hp">About:</h3>The purpose of this LoRA is to <s>(try to)</s> closely replicate the appearance of Gianna Michaels, a famous adult movie actress.It was trained in multires (512 up to 1024), using simple captions and with 54 high-resolution images.The demo images of the LoRA aren't edited, but they are cherry-picked and generated using hires-fix (0.25 ~ 0.45 denoising).<h3 id="suggested-settings-for-inference:-uvmk6maqr">Suggested Settings for Inference:</h3>Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/25694?modelVersionId=134065">epicrealism_pureEvolutionV5</a> (but works with 97,2% of models)Positive: a woman with winter clothes, gianna michaels, fully clothed, head and chest only, private press &lt;lora:Gianna_Michaels_SD15_by_IsnAI:1&gt;Negative: (cleavage, nsfw, topless, nude, naked)Sampler: DPM++ 2M KarrasSteps: 32CFG: 7 (5 ~ 7)Resolution: 640x960Upscaler: 4x_NMKD-Siax_200kNote: Applying high denoising values (0.45~) in hires-fix enhances the appearance fidelity.<h3 id="trigger:-j4p88s0w4">Trigger:</h3>Main: gianna michaels

Files with SHA256: 5a4358800ed070995de71b8e89fac0068e0d52cb63aa892f67777f93c4586f2c