santa hat
deerdeer nosedeer glow
Sign In

SDXL_fixedvae_fp16(Remove Watermark)

856
10.3k
92
Updated: Oct 5, 2024
basemodelsdxl
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
6,116
Reviews
Published
Jul 30, 2023
Base Model
SDXL 1.0
Hash
AutoV2
1FA5725F4F
default creator card background decoration
SDXL Training Contest Participant
bdsqlsz's Avatar
bdsqlsz

This is merge model for:

1. 100% stable-diffusion-xl-base-1.0 and 100% stable-diffusion-xl-refine-1.0

https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0

https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0

2. sdxl-vae-fp16-fix

https://huggingface.co/madebyollin/sdxl-vae-fp16-fix

you can use this directly or finetune.

same license on stable-diffusion-xl-base-1.0

same vae license on sdxl-vae-fp16-fix

SDXL-VAE-FP16-Fix

SDXL-VAE-FP16-Fix is the SDXL VAE, but modified to run in fp16 precision without generating NaNs.

VAEDecoding in float32 / bfloat16 precisionDecoding in float16 precisionSDXL-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:

1. keep the final output the same, but

2. make the internal activation values smaller, by

3. 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.

Benchmark from here:by Kubuxu

https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7

Evaluation on COCO val-2017, 256x256, RandomCrop with padding
Metrics:
LPIPS:
https://github.com/richzhang/PerceptualSimilarity/ (lower better) and structural similarity index measure via skimage.metrics (higher better)
Metrics given as: mean [79% credibility interval]