How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
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

sample image

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
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for atsushi015/hypernetwork-quality-tags

Finetuned
(2)
this model