Soft & Fast VAE (80MB Quantized)
VAE was trained and quantized with mixed block precision (F8_E5M2 & F8_E4M3)
VAE is extremely accurate for quantized VAE
The VAE has some saturation increase from BASE SDXL and a softer appearance.
Soft & Fast VAE (SDXL/PONY 80MB Quantized)
DEFAULT
The model deployment is abnormal, please re-upload/contact customer service.
Version Detail
Pony
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges