update cifar generated images figure

atong01 · Oct 31, 2023 · 734a711 · 734a711
1 parent 5cd0e6f
commit 734a711
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -26,7 +26,7 @@
 Conditional Flow Matching (CFM) is a fast way to train continuous normalizing flow (CNF) models. CFM is a simulation-free training objective for continuous normalizing flows that allows conditional generative modeling and speeds up training and inference. CFM's performance closes the gap between CNFs and diffusion models. To spread its use within the machine learning community, we have built a library focused on Flow Matching methods: TorchCFM. TorchCFM is a library showing how Flow Matching methods can be trained and use to deal with image generation, single-cell dynamics and (soon) SO(3) data and tabular data.
 
 <p align="center">
-<img src="assets/169_generated_samples_otcfm.gif" width="600"/>
+<img src="assets/169_generated_samples_otcfm.png" width="600"/>
 <img src="assets/8gaussians-to-moons.gif" />
 </p>
 

diff --git a/assets/169_generated_samples_otcfm.png b/assets/169_generated_samples_otcfm.png
diff --git a/examples/cifar10/README.md b/examples/cifar10/README.md
@@ -3,7 +3,7 @@
 This repository is used to reproduce the CIFAR-10 experiments from [1](https://arxiv.org/abs/2302.00482). We have designed a novel experimental procedure that helps us to reach an __FID of 3.5__ on the Cifar10 dataset.
 
 <p align="center">
-<img src="../../assets/169_generated_samples_otcfm.gif" width="600"/>
+<img src="../../assets/169_generated_samples_otcfm.png" width="600"/>
 </p>
 
 To reproduce the experiments and save the weights, install the requirements from the main repository and then run (runs on a single RTX 2080 GPU):