Riley Reid - Adult Film Actress, Images made with Fooocus
General Fooocus settings:
"prompt": "score_9, score_8_up, score_7_up, photo realistic, true to life, 1girl, reilyreid, 1girl, skinny, solo, brown hair, jewelry, necklace, dress, bracelet, makeup, green eyes, long hair, dress, parted lips, headshot, looking at viewer",
"negative_prompt": "score_4, score_5, score_6, logo, (((cleavage:1.5))), nude, nipples. show leg, watermark, signature, blurred eyes, lowres, low detail, blurry, watercolor, thick thighs, bad anatomy, bad proportions, deformed, deformed anatomy, deformed fingers, deformed faces, blurry faces, undefined, combined bodies, two heads, conjoined twins, headless. head without body, ugly face, no pupils, missing eyes, six fingers. six toes, unrealistic, saturated, high contrast, painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label",
"prompt_expansion": "",
"styles": "[]",
"performance": "Quality",
"resolution": "(832, 1216)",
"guidance_scale": 7,
"sharpness": 10,
"adm_guidance": "(1.5, 0.8, 0.3)",
"base_model": "ponyRealism_v21VAE.safetensors",
"refiner_model": "anirealPony_v1.safetensors",
"refiner_switch": 0.5,
"clip_skip": 2,
"sampler": "dpmpp_2m_sde_gpu",
"scheduler": "karras",
"vae": "Default (model)",
"seed": "5522865086367865411",
"lora_combined_1": "Riley_Reid-000008.safetensors : 1.0",
"metadata_scheme": false,
"version": "Fooocus v2.4.3"
Description
FAQ
Comments (2)
Looks damn accurate after adetailer makes the final adjust.
It's close to impossible to train realistic people with PonyXL. Mainly because the gap between the huge understanding of the "eyes" concept in Pony, and realistic eyes, simply doesn't match.
BUT, it's fucking great nonetheless to train with Pony because then you know the anatomy part will be perfect.
Thanks for training her. An advice if I may (that's what I do): use the same database to train an SDXL version of her. This way there are both a Pony version for txt2img, img2img, inpaint, etc. most of the creation process. But then there is an SDXL version to inpaint the final realistic touch with a low denoising. Combination of Pony + SDXL LoRAs of the same person is the only way to create a realistic image of her with a realistic face ;)
Cheers.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.