Downloads · 30 days
6
2% of all-time downloads
sd3_randn_aura_vae
Disty0/sd3_randn_aura_vae
sd3_randn_aura_vae is a text-to-image model from Disty0. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as cc-by-sa-4.0.
An anime model trained on randomly initialized SD3 Transformer weights with RMSNorm and AuraDiffusion 16ch VAE. Trained on 256px resolutions using anime dataset.
All-time downloads
256
Public
Parameters
2.1B
24 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors19.8 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- cc-by-sa-4.0
- Access
- Public
- Created
- Jul 2, 2024
- Updated
- Jul 30, 2024
- SHA
- ea0c2cd7
Model card
From the Hugging Face model README
An anime model trained on randomly initialized SD3 Transformer weights with RMSNorm and AuraDiffusion 16ch VAE.
Trained on 256px resolutions using anime dataset.
Requires Diffusers with RMSNorm support: https://github.com/Disty0/diffusers/tree/sd3_rms_norm
- Task
- Text-to-Image
- Library
- diffusers
- License
- cc-by-sa-4.0
- Created
- Jul 2, 2024
- Updated
- Jul 30, 2024