Lora model trained with flux, will generate images, photographs, perfect faces, natural and straight hair, perfect eyes and eyelashes, medium and delicious breasts!400 high quality images were used, with faces and hair in different color tonesResolution settings:Standard resolutions 512 x 768, 768 x 512, 540 x 960 and 1024 x1024Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixelsResolution: 540x960 select the Hires.fix checkbox, result 1080 x 1920 pixelsUse these recommended settings for generation:Sampling method: Euler_MaxSampling steps: 30-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: Euler_Smea_DySampling steps: 30-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: Euler aSampling steps: 30-50CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: LCMSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DDPM KarrasSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 2M KarrasSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ SDE KarrasSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 2M SDE KarrasSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 2M SDE ExponentialSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 3M SDESampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 3M SDE KarrasSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Sampling method: DPM++ 3M SDE ExponentialSampling steps: 20-30CFG Scale: 2.0 - 7.0Skip clip: 1-2Recommended negative prompts:(CyberRealistic_Negative-neg), cartoon, painting, illustration, (grayscale:1.4), (worst quality:2), (low quality:2), (normal quality:2), ugly, fat, 3D rendering, asian;

DXMakeup

V1. It has no flaws, I ask that you test and make the most of this Lora model.

Files with SHA256: f25f40f6e90f2bb20159503431fd9bacb7dd4847145dbaca83054803511b8134