| --- |
| license: cc |
| library_name: diffusers |
| tags: |
| - art |
| model-index: |
| - name: 16ch-VAE |
| results: |
| - task: |
| type: encoder-loss |
| dataset: |
| name: yerevann/coco-karpathy |
| type: image |
| metrics: |
| - name: PSNR |
| type: PSNR |
| value: 31.5151 |
| --- |
| |
| ## 16ch-VAE |
|
|
| > Disclaimer: this VAE is not intended to be a replacement for SD3's VAE since the latent spaces are entirely different. |
|
|
| A fully open source 16ch VAE reproduction for the [SD3](https://arxiv.org/abs/2403.03206). Useful for people who are building their own image generation models and need an off-the-shelf VAE. Natively trained in fp16. |
|
|
|
|
| | VAE | rFID | PSNR | LPIPS | |
| |------------------|--------|---------|--------| |
| | SD1.5 VAE | 0.3131 | 26.4332 | 0.0328 | |
| | SDXL VAE | 0.3511 | 26.7577 | 0.032 | |
| | SD3 VAE | 0.0257 | 30.3231 | 0.0132 | |
| | [16ch-VAE](https://huggingface.co/AuraDiffusion/16ch-vae) | 0.0667 | 31.5151 | 0.0136 | |
| | [16ch-VAE with FFT](https://huggingface.co/AuraDiffusion/16ch-vae)* | 0.1584 | 31.0542 | 0.0281 | |
|
|
|
|
| ### Usage |
|
|
| Awaiting https://github.com/huggingface/diffusers/pull/8769 in diffusers! |
