Pinned Loading

1. taesdtaesdPublic

   Tiny AutoEncoder for Stable Diffusion (and other image models)

   Python 969 52

2. taehvtaehvPublic

   Tiny AutoEncoder for Hunyuan Video (and other video models)

   Python 526 21

3. maple-diffusionmaple-diffusionPublic

   Stable Diffusion inference on iOS / macOS using MPSGraph

   Swift 822 54

4. dino-diffusiondino-diffusionPublic

   Bare-bones diffusion model code

   Jupyter Notebook 160 14

5. seraenaseraenaPublic

   WIP Pytorch code for stably training single-step, mode-dropping, deterministic autoencoders

   Jupyter Notebook 50 6

6. notes_on_sd_vaenotes_on_sd_vae

   1

   # Notes / Links about Stable Diffusion VAE

   2

   3

   Stable Diffusion's VAE is a neural network that encodes images into a compressed "latent" format and decodes them back. The encoder performs 48x lossy compression, and the decoder generates new detail to fill in the gaps.

   4

   5

   ![](https://user-images.githubusercontent.com/8733615/281488415-ea77f359-d380-412d-b27a-21884d19da1d.jpg)