SDXL_anime_vae

These are VAE (Variational Autoencoder) for the SDXL animation model.

SDXL_anime_natural_vae

This is a VAE that significantly reduces the yellow-green color cast present in the original SDXL_0.9_vae.

It also minimizes image degradation compared to the original SDXL_0.9_vae.

It is particularly effective in workflows where the VAE is used multiple times, such as with Hires.Fix, Detailer, and similar processes.

SDXL_anime_clear_vae

mellow_pencil-XL-v1.0.0-base_clear_upscale_1
mellow_pencil-XL-v1.0.0-base_clear_upscale_2

Compare to SDXL_Base_0.9_vae (Original)

SDXL_clear_vae_girl
SDXL_original_vae_girl

SDXL_clear_vae | SDXL_Base_0.9_vae (Original)

SDXL_clear_vae_bird
SDXL_original_vae_bird
SDXL_clear_vae_compare_bird_close_up

It features clearer rendering compared to the original, and is characterized by a deeper color expression, primarily in reds.

However, in fine detail, there is a slight tendency for detail to be subtly crushed or lost.


Base Model


Tips (External site)


License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Space using easygoing0114/SDXL_anime_vae 1