import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("atsushi015/hypernetwork-quality-tags", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]quality-tags
A hypernetwork dedicated for quality enhancing (instead of using quality tags)
This hypernetwork model is intended for replacing quality annotation tags like 4K, ultra-detailed, masterpiece etc...
You can use this model to make detailed art style images without these tags.
(2025/03/09) Updated. 7th Layers compatible.
Example image informations.
Prompt: 1 girl, white hat with blue ribbon, whire summer dress, corsage, sea, beach, sunlight
Base model: 7th_Anime_v3
Note that the prompt doesn't contains tags which suggesting about qualities.
- Downloads last month
- -
Model tree for atsushi015/hypernetwork-quality-tags
Base model
hakurei/waifu-diffusion