A model of Pirate Tawna, trained over 21 images for 1024 using NoobAI Epsilon-pred 1.1 as a training modelTrigger word: ptcaoLooks tags: furry female, two-tone fur, orange fur, white fur, two-tone hair, blonde hair, blue hair, mohawk, blue eyes, snout, multiple earrings, mole under eyeClothes tags: brown leather jacket, cropped jacket, spikes, sleeves rolled up, pink top, blue bandana, brown partially fingerless gloves, brown belt, multiple belts, torn jeans, thigh strap, thigh pouch, pink leg warmer, brown footwearWeight: 1 is perfectAdditional information:Webui I useAAA Anime VAE SDXL v2 as VAESampling method: Euler aSchedule type I set it to Align Your StepsSampling steps I go 20-304xNomos8kDAT as an UpscalerHires steps I go 8-15 (I don't always use hires fix)Denoising strength I go 0.4Upscale by 1.2 to 2.0 depending on the starting image dimensionsImagine dimensions vary depending on what I'm trying to doI use 6 CFG Scaleuddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full faceIf you wanna support me or request a commission ko-fi
Description
A model of Pirate Tawna, trained over 21 images for 1024 using NoobAI Epsilon-pred 1.1 as a training modelTrigger word: ptcaoLooks tags: furry female, two-tone fur, orange fur, white fur, two-tone hair, blonde hair, blue hair, mohawk, blue eyes, snout, multiple earrings, mole under eyeClothes tags: brown leather jacket, cropped jacket, spikes, sleeves rolled up, pink top, blue bandana, brown partially fingerless gloves, brown belt, multiple belts, torn jeans, thigh strap, thigh pouch, pink leg warmer, brown footwearWeight: 1 is perfectAdditional information:Webui I useAAA Anime VAE SDXL v2 as VAESampling method: Euler aSchedule type I set it to Align Your StepsSampling steps I go 20-304xNomos8kDAT as an UpscalerHires steps I go 8-15 (I don't always use hires fix)Denoising strength I go 0.4Upscale by 1.2 to 2.0 depending on the starting image dimensionsImagine dimensions vary depending on what I'm trying to doI use 6 CFG Scaleuddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full faceIf you wanna support me or request a commission ko-fi