This is AIO file (Diffusion Model+TextEncoder+VAE) for convenience. Enjoy PonyV7!
Original Resources are below:
Notice:
2025/1/3
Scaled fp8 Diffusion Model + fp16 TextEncoder + fp16 VAE is now available, have fun!
2025/1/2
I finally found the origin of the problem. In fp8 quantization of PonyV7, we need "scaled fp8". Otherwise, it'll break the critical part of the model weight.
2025/12/31
Currently, fp16 AIO has no saturation problem. And, I'll try to recreate correct fp8 AIO.
2025/12/31
I found image saturation problem in fp8 AIO, so I'll upload fixed version for that.
Description
I found image saturation problem in this version, so I'll upload fixed version for that.
FAQ
Comments (8)
Does one use Pony 7?
I am, at least ;-)
can this model do anything yet?
v7.0_fp16(AIO) in this page will works fine. But original PonyV7 itself is still unstable, so this AIO file is unstable, too. I hope that the PonyV7.1 will be nice.
I'd use https://github.com/silveroxides/convert_to_quant instead of trying scaled
Thank you! I'll try it!
@JohnDoeSmith Could you share the script to make fp8 scaled?
@qek O.K. I'll upload it to GitHub, later.