For best outputs and usage:

Sampler: Euler a.

Steps: 25, cfg 7, CLIP skip 2.

VAE: none required.

Pos prompt: wrap your text between "score_9, score_8_up, score_7_up, source_real, Perfect Hands, detailed, realistic photograph, (realistic photography), (dynamic_pose), source_real" and "realistic, (dramatic lighting:1.6), rating_explicit, (depth of field:1.2), epiCPhoto, ", being the embedding "epiCPhoto" and the LoRa "add-detail-xl" found in my example runs.

Neg prompt: "score_3, score_2, score_1, source_anime, source_cartoon, mosaic censoring, bar censoring, censored, text, signature, logo, artist_name, username, crop, frame, (simple background:1.6), worst quality, low quality, normal quality, messy drawing, amateur drawing, lowres, bad anatomy, bad hands, source filmmaker, 3d, old woman, granny, showing teeth, muscles, censor, bar censor, mosaic censorship, fat, BeyondSDXLv3, epiCNegative", being the embeddings "BeyondSDXLv3" and "epiCNegative" found in my example runs.

Checkpoint Merge.