The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
LTXV VAE decoder: switch default padding mode (#8930)
Harel Cain9bc2798f7294
diff --git a/comfy/ldm/lightricks/vae/causal_video_autoencoder.py b/comfy/ldm/lightricks/vae/causal_video_autoencoder.pyindex f91870d71..75ed069ad 100644--- a/comfy/ldm/lightricks/vae/causal_video_autoencoder.py+++ b/comfy/ldm/lightricks/vae/causal_video_autoencoder.py@@ -973,7 +973,7 @@ class VideoVAE(nn.Module):norm_layer=config.get("norm_layer", "group_norm"),causal=config.get("causal_decoder", False),timestep_conditioning=self.timestep_conditioning,- spatial_padding_mode=config.get("spatial_padding_mode", "zeros"),+ spatial_padding_mode=config.get("spatial_padding_mode", "reflect"),)self.per_channel_statistics = processor()