Downloads · 30 days
0
DDBM
alexzhou907/DDBM
DDBM is a machine learning model from alexzhou907. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repo contains checkpoints from Denoising Diffusion Bridge Models \(DDBM\).
Access
Public
Updated Feb 25, 2024
Repo size
8.3 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.npz4.9 GB · 59%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 29, 2023
- Updated
- Feb 25, 2024
- SHA
- f1717e86
Model card
From the Hugging Face model README
Overview
This repo contains checkpoints from Denoising Diffusion Bridge Models (DDBM).
<p align="center"> <img src="assets/DDBM_teaser.png" width="100%"/> </p>We provide here pretrained checkpoints for the image-to-image translation experiments conducted in the paper.
- DDBM trained on Edges2Handbags using Variance-Preserving (VP) schedule
- DDBM trained on DIODE using Variance-Preserving (VP) schedule
- Reference statistics for Edges2Handbags
- Reference statistics for DIODE
Datasets
Please follow the provided links above to download respective datasets.
Evaluation
We provide the reference statistics. For evaluation against the reference stats, please follow the repo here.
- License
- mit
- Created
- Sep 29, 2023
- Updated
- Feb 25, 2024