Downloads · 30 days
51
1% of all-time downloads
kotosmix_diffusers
digiplay/kotosmix_diffusers
kotosmix_diffusers is a text-to-image model from digiplay. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
model info : https://civitai.com/models/5245/kotosmix
All-time downloads
4.7K
Public
Parameters
860M
18.6 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors10.4 GB · 56%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- May 29, 2023
- Updated
- Jun 19, 2023
- SHA
- ee3e6422
Model card
From the Hugging Face model README
model info : https://civitai.com/models/5245/kotosmix
you can apply VAE to get better color,
example codes for diffusers:
#VAE
from diffusers.models import AutoencoderKL
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")
modelid="digiplay/kotosmix_diffusers"
pipe = DiffusionPipeline.from_pretrained(modelid, vae=vae)
PS: Recommended Euler scheduler type.
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Created
- May 29, 2023
- Updated
- Jun 19, 2023