I present the model Lora Olga trained with 615 high quality photos, realistic and photographic model!<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">Note: Olga is a fictional model who doesn't exist in the real world!The vae is already included in the model, or use the one of your preferenceTo activate the model you need to insert the token "olwrs" and the class "woman"recommended strength:olwrs&lt;lora:olga:0.9&gt;olwrs&lt;lora:olga:0.8&gt;olwrs&lt;lora:olga:0.7&gt;olwrs&lt;lora:olga:0.6&gt;I recommend using the <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a> extension.Use this extension to fix hand errors:<a target="_blank" rel="ugc" href="https://github.com/licyk/advanced_euler_sampler_extension">https://github.com/licyk/advanced_euler_sampler_extension</a>It is strictly prohibited to distribute, inside and outside civit ai, this template or post it anywhere or on hosting services, on third party image generation services, you can use it for personal use, if you know who distributed it without my consent , report it immediately.Resolution settings:Standard resolutions 512 x 768, 768 x 512, 540 x 960, 640 x 960, 960x640 and 1024 x1024Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixelsNote: I am testing the sampling methods and I will add the others to the settings.Use these recommended settings for generation:Sampling method: RestartSampling steps: 30-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: Kohaku_LoNyu_YogSampling steps: 30-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: Euler_MaxSampling steps: 30-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: Euler_Smea_DySampling steps: 18-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: Euler aSampling steps: 18-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: LCMSampling steps: 18-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DDPM KarrasSampling steps: 18-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 2MSampling steps: 18-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ SDE KarrasSampling steps: 18-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 2M SDE KarrasSampling steps: 18-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Use the recommended negative prompt:(CyberRealistic_Negative-neg), cartoon, painting, illustration, (grayscale:1.4), (worst quality:2), (low quality:2), (normal quality:2), ugly, fat, 3D rendering, asian, body multiplication, arms multiplied, neck with, long neck, nude, naked, chinese, japanese, asian, colored background, multiplied fingers, bad fingers, multiplied head, duplicate tail,malformed ears, bad horns, red skin, clean clothing, smooth fabric, realistic folds, high detail, glasses, nude

Model Olga

Lora model trained with 615 high-resolution images, pony version, realistic and photographic, generates images of thin bodies, small and large breasts!To activate the model you need to insert the token "mdlolg" and the class "woman"recommended strength:mdlolg&lt;lora:model olga xl:0.6&gt;mdlolg&lt;lora:model olga xl:0.7&gt;mdlolg&lt;lora:model olga xl:0.8&gt;mdlolg&lt;lora:model olga xl:0.9&gt;I recommend using the <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a> extension.

Files with SHA256: 6b1d038ebe9e8534a54a86cdee385661497493ad9a80c1005b78394eb5f8a49f