Downloads · 30 days
9
0% of all-time downloads
Hemlok/QuinceMix
QuinceMix is a text-to-image model from Hemlok. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
- "Defacta"ベースのマージモデルです。 - 背景やエフェクトに強いモデルです。
Downloads · 30 days
9
0% of all-time downloads
All-time downloads
31.8K
Public
Repo size
14 GB
Likes
22
Public
Click a slice to open those files.
.bin5.5 GB · 39%
From the Hugging Face model README


(masterpiece, ultra high res, best quality:1.1), (flat color:1.4), 1girl, solo, teen, cowboy shot, (depth of field:1.2), (night), downtown, (street light:1.1), (Fantastic lighting), looking at viewer, (school uniform), black hair, long hair, [smile], (Closed mouth)

(masterpiece, ultra high res, best quality:1.1), 1girl, solo, (fantasy), (dark:1.2), (horror:1.2), (depth of field:1.2), (night), (water effect:1.2), (Fantastic lighting), looking at viewer, white hair, long hair,
from diffusers import StableDiffusionPipeline
import torch
model_id = "Hemlok/QuinceMix"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "One girl standing by the window"
image = pipe(prompt).images[0]
image.save("test.png")