Downloads · 30 days
0
stylegan3_conditional_MNIST
oweissl/stylegan3_conditional_MNIST
stylegan3_conditional_MNIST is a text-to-image model from oweissl. Use it when you need an image from a text prompt. The card lists the license as unknown.
This model allows to generate MNIST-like images. The model is based on StyleGAN3-t and used the MNIST training split padded to 32x32. The prepared dataset can be found here.
Access
Public
Updated Oct 31, 2024
Repo size
788 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl400 MB · 100%
At a glance
- Task
- Text-to-Image
- License
- unknown
- Access
- Public
- Created
- Oct 30, 2024
- Updated
- Oct 31, 2024
- SHA
- b1796c0e
Datasets
Model card
From the Hugging Face model README
Model Card for conditional StyleGAN3-t-MNIST
<!-- Provide a quick summary of what the model is/does. -->This model allows to generate MNIST-like images. The model is based on StyleGAN3-t and used the MNIST training split padded to 32x32. The prepared dataset can be found here.
The model was trained using the following parameters:
- gamma: 0.125
- kimg: 5000
- cbase: 16384
- batch: 128
- metrics: fid50k (3.623 final)
This training took ~12h on 2 Nvidia A100 GPU
- Task
- Text-to-Image
- License
- unknown
- Created
- Oct 30, 2024
- Updated
- Oct 31, 2024