imagine
SD checkpoint
·
Uploaded May 25, 2024
·
Used 316 times
About this version
For best outputs:
Sampler: DPM++ 2M Karras.
Steps: 25, cfg 3.5, CLIP skip 2.
VAE: none required.
Pos prompt: just what you want to see. This model is capable of realism, photorealism (with photorealism keywords), anime, cartoon, and many art styles, since it's a versatile model.
Neg prompt: "nsfw, nipples, cartoon, painting, illustration, (grayscale:1.4), (worst quality:2), (low quality:2), (normal quality:2), ugly, fat, 3D rendering" (change "cartoon" by "realistic" when doing cartoon / anime, and remove "painting, illustration" if you're attempting art styles like ink drawing).
Checkpoint Trained.
Related Posts