metadata

license: other
datasets:
  - p1atdev/pvc
language:
  - en
library_name: diffusers
tags:
  - text-to-image
  - stable-diffusion
  - safetensors

PVC v3

This model is a latent diffusion model finetuned on Waifu Diffusion v1.5 beta 2 with PVC figure images. You can use Danbooru tags to generate images.

Downloads

Prompt guide

Trigger words

pvc means the pvc material style but not needed always.
figma is the figure style that has joints, and more tend to be product thumbnail images.
nendoroid means the style of chibi figures. Use with chibi to get better results.

Tips

The PVC figure style is closer to the anime style than to the realistic style. So, it is recommended to put anime to positive prompt and realistic to negative prompt to get better results sometimes. If you want to avoid too realistic faces, try this! Setting realistic to negative does not affect the pvc style, only the faces of the characters.

Examples

Training information

Parameter	Value
Service	Runpod
GPU	A5000
Notebook	Linaqruf/kohya-trainer
Cost	about $2
Hours	about 6 hours
Dataset	7467 images from p1atdev/pvc
Resolution	896
Epochs	5
Optimizer	Lion
LR	4e-7
Scheduler	cosine_with_restarts
Train Batch Size	1

License

PVC v3 is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.