built-in-nodes/VAEEncode #1681
Replies: 2 comments 2 replies
|
VAE 是一种数据转换模型( variational autoencoder model),用于在图像数据在 Latent-Space 与 Pixel-Space 之间进行转换。 一般认为VAE编码,是指将像素空间数据(Pixel-Space)转为 潜空间表示数据(Latent-Space);逆操作称为VAE解码,即将潜空间表示数据(Latent-Space)转为像素空间数据(Pixel-Space)。 |
2 replies
|
Hi @Nuos, thanks for the detailed follow-up — that is exactly the right mental model. To confirm and summarize:
We appreciate you taking the time to verify this against the original paper (https://arxiv.org/abs/1312.6114) and share it here. If you feel the VAEEncode doc page could be clearer on any of these points, please let us know — suggestions like this are very welcome. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
built-in-nodes/VAEEncode
This node is designed for encoding images into a latent space representation using a specified VAE model.
https://docs.comfy.org/built-in-nodes/VAEEncode
All reactions