Another take on upscaler using AsymmetricAutoencoderKL, in this case I did re-use decoder of ostris/vae-kl-f8-d16 as decoder and trained just encoder.
Oversharpening was reduced by usage of sobel in loss calculation. I guess that without high resolution image used as reference, it might look more blury than previous one.
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Heasterian/AsymmetricAutoencoderKLUpscaler_v2
Base model
ostris/vae-kl-f8-d16