metadata
license: mit
tags:
- stable-diffusion
- stable-diffusion-diffusers
inference: false
SDXL-VAE-FP16-Fix
SDXL-VAE-FP16-Fix is the SDXL VAE, but modified to run in fp16 precision without generating NaNs.
| VAE | Decoding in float32 / bfloat16 precision |
Decoding in float16 precision |
|---|---|---|
| SDXL-VAE | ✅  |
⚠️  |
| SDXL-VAE-FP16-Fix | ✅  |
✅  |
Details
SDXL-VAE generates NaNs in fp16 because the internal activation values are too big:
SDXL-VAE-FP16-Fix was created by finetuning the SDXL-VAE to:
- keep the final output the same, but
- make the internal activation values smaller, by
- scaling down weights and biases within the network
There are slight discrepancies between the output of SDXL-VAE-FP16-Fix and SDXL-VAE, but the decoded images should be close enough for most purposes.