Files
ComfyUI-SelVA/nodes
Ethanfel 43f732f904 fix: transpose VAE latent from [B,C,T] to [B,T,C] before generator
VAE encoder returns channels-first [B, latent_dim, T]; the generator
expects time-first [B, T, latent_dim] (same convention as decode which
already does .transpose(1,2)). Fixes normalize() size mismatch.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-05 22:08:00 +02:00
..