Downloads · 30 days
0
bad-artist
nick-x-hacker/bad-artist
bad-artist is a text-to-image model from nick-x-hacker. Use it when you need an image from a text prompt. The card lists the license as cc0-1.0.
Access
Public
Updated Dec 12, 2022
Repo size
14.2 KB
Likes
316
Public
Repo makeup
Click a slice to open those files.
.pt14.2 KB · 83%
At a glance
- Task
- Text-to-Image
- License
- cc0-1.0
- Access
- Public
- Created
- Dec 12, 2022
- Updated
- Dec 12, 2022
- SHA
- e0186f43
Model card
From the Hugging Face model README
bad-artist 'negative' embedding
Model Card WIP.
The images above were generated with only "solo" in the positive prompt, and "sketch by bad-artist" (this embedding) in the negative. <br/> The embedding uses only 2 tokens.
Textual-inversion embedding for use in unconditional (negative) prompt. <br/> 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
- Task
- Text-to-Image
- License
- cc0-1.0
- Languages
- eng
- Created
- Dec 12, 2022
- Updated
- Dec 12, 2022