Portrait of a young man with aqua hair and tanned skin wearing a blue suit and gold necklace, sitting in a luxury strip club with velvet booths and low lighting.
Close-up portrait of a blonde girl with devil horns, freckles, and black lipstick wearing a black leather jacket and a white top against a dark blue background with bubbles.
A detailed close-up back view of a woman with long white hair styled up, adorned with gold dragon horns and jewelry, wet skin glistening, wearing a sheer black robe.
A redhead female kitsune with fox ears and freckles wearing a white Japanese kimono, seated in a night Sakura garden with flowers in her hair.
Anime girl with brown hair and in a white tank top relaxing barefoot in a cozy room surrounded by stacks of books. AI generated image using Stable Diffusion.
Anime-style blonde girl with green eyes, wearing a white and gold outfit, and sitting with her feet up, showing soles. AI generated image using Stable Diffusion.
Anime-style AI generated image featuring a girl with black hair and red glasses, displaying her feet close-up while she lies on a bed. Created using Stable Diffusion.
Anime girl with devil horns, sitting with feet stretched out, surrounded by books. AI generated image using Stable Diffusion.
An AI generated image using stable diffusion depicting an anime-style girl with dark hair tied in buns, purple eyes, and a playful expression, with a close-up view of her feet in the foreground.
AI-generated image of an anime woman with glasses, wearing a pink turtleneck sweater and a white apron, holding a utensil in a modern kitchen. Stable Diffusion generated.

Tips

Use only the one positive embedding for new V3 versions.

Embeddings do not duplicate each other, so you can combine multiple together as needed.

Recommend using both positive and negative embeddings together at strength 1.0 to 2.0; if unable to use both, prioritize the positive embedding.

These embeddings don't work with non-Pony models; check your model compatibility.

No need to use score this, and score that. Just use the embeddings instead.

New V3 versions only need the one positive embedding!.

A set of quality enhancing embeddings for Pony SDXL, and other Pony-Adjacent models. You can mix and match any of the embeddings that you feel you need. They don't duplicate each other, so feel free to use as many together as needed.

High Quality V3 (zPDXL3): gives higher quality results and removes annoying censoring.

XXX Rating: tells the Pony model of your choice to allow NSFW content.

PG Rating: tells the Pony model of your choice to try and remove NSFW content for safe images.

Photo Real: tells the Pony model of your choice to use realistic or near realistic renders instead of cartoon or anime.

High Quality V2 (old): designed to give higher quality results and remove censoring.

Doesn't work with non-Pony models. Check your model.

Recommend using both positive and negative embeddings together at strength 1.0 to 2.0. If you can't use both, the Positive version should be take priority.

Contributor

Previous
FLUX.1 [dev] fp8 versions - Scaled fp8/fp8_e4m3fn/fp8_e5m2 - fp8_e4m3fn
Next
FLUX.1d - Blurry Photos - V1

Model Details

Model type

TextualInversion

Base model

Pony

Model version

XXX Rating

Model hash

000e2b1616

Trained words

zPDXLxxx

Creator

Discussion

Please log in to leave a comment.