models/Bad artist Negative embedding - Bad artist

Bad artist Negative embedding - Bad artist

|
7/4/2025
|
9:30:47 AM
| Discussion

Recommended Prompts

solo

Recommended Negative Prompts

sketch by bad-artist

Recommended Parameters

samplers

DPM++ 2M Karras

steps

15

cfg

4

resolution

512x640

Tips

Use 'by bad-artist' in the prompt, e.g. 'sketch by bad-artist', 'painting by bad-artist', or 'photograph by bad-artist'.

The embedding uses only 2 tokens for text inversion.

There are two versions: 'bad-artist' for uniqueness and 'bad-artist-anime' for generic anime style.

I AM NOT THE ORIGINAL CREATOR OF THIS EMBEDDING

HE IS -

https://huggingface.co/nick-x-hacker/bad-artist

The images above were generated with only "solo" in the positive prompt, and "sketch by bad-artist" (this embedding) in the negative.
The embedding uses only 2 tokens.

Textual-inversion embedding for use in unconditional (negative) prompt.
Inspired partly by https://huggingface.co/datasets/Nerfgun3/bad_prompt.

There are currently 2 version:

  • 'bad-artist': Not as strong, but produces pretty unique images (recommended)

  • 'bad-artist-anime': More generic anime style (this was the first version uploaded)

I recommend using with 'by', so for example "sketch by bad-artist", or "painting by bad-artist", or "photograph by bad-artist", etc.

Trained with 2 vectors per token for 15000 (1850x8) steps, at 500x500, on an Anything-v3-based model.

Full generation parameters for images above (using the 'bad-artist' version, not the 'bad-artist-anime' version):

solo
Negative prompt: sketch by bad-artist
Steps: 15, Sampler: DPM++ 2M Karras, CFG scale: 4, Seed: 1476197242, Size: 512x640, Clip skip: 2

Contributor

Previous
Teeth XL - Teeth XL
Next
Chiaroscuro (Contrasted) Lighting Style XL + F1D + Illu + Pony - Chiaroscuro XL v1.0

Model Details

Model type

TextualInversion

Base model

SD 1.5

Model version

Bad artist

Model hash

2d35613490

Trained words

By bad artist

Creator

Discussion

Please log in to leave a comment.