Retrained with 150 images for a better overall look.
Lana Rhoades - Adult Film Actress. Images made in Foocus. Trained on over 500 150 images with backgrounds removed for V2.
I'm not sure why I didn't realize I'm adding way too many images for character models. 500 is great for a concept but way too much for a character model. So I'm limiting myself to 100-150 from here on out to avoid "overcooked" look but still get a good amount of posing data. I plan to go back and retrain other models that don't look that great as time allows.
General Fooocus settings:
"prompt": "score_9, score_8_up, score_7_up, photo realistic, true to life, highly detailed. solo. 1girl, LanaRhoades, brunette, long straight hair, , thin waist, blue eyes, eye symmetry, eyeliner, lipstick, skin texture, face, at the beach. headshot, face focus., looking away from camera, wearing a black tshirt. in a forest",
"negative_prompt": ", midriff, (((:1.5))), ., unrealistic, saturated, high contrast, big nose, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label",
"prompt_expansion": "",
"styles": "[]",
"performance": "Quality",
"steps": 60,
"resolution": "(832, 1216)",
"guidance_scale": 7,
"sharpness": 10,
"adm_guidance": "(1.5, 0.8, 0.>
"base_model": "ponyRealism_v21VAE.safetensors",
"refiner_model": "anirealPony_v3.safetensors",
"refiner_switch": 0.5,
"clip_skip": 2,
"sampler": "dpmpp_2m_sde_gpu",
"scheduler": "karras",
"vae": "Default (model)",
"seed": "6424619604019089077",
"freeu": "(1.01, 1.02, 0.99, 0.95)",
"lora_combined_1": "Lana_Rhodes.safetensors : 1.0",
"metadata_scheme": false,
"version": "Fooocus v2.5.0"
Retrained with 150 images for a better overall look.
1. Quyền đối với các mô hình được đăng lại thuộc về người sáng tạo ban đầu.
2. Người sáng tạo gốc muốn xác nhận mô hình vui lòng liên hệ nhân viên SeaArt AI qua kênh chính thức. Nhấp để xác nhận
