fix: enable VAE encoder in model loader — required for DITTO reference encoding

need_vae_encoder=False was deleting the encoder to save a small amount of VRAM.
DITTO now needs it to encode reference clips to latent space for style loss.
The spectrogram VAE encoder is small enough that the overhead is negligible.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

nodes/selva_model_loader.py

@@ -149,7 +149,7 @@ class SelvaModelLoader:
             enable_conditions=True,
             mode=mode,
             bigvgan_vocoder_ckpt=bigvgan_path,
-            need_vae_encoder=False,
+            need_vae_encoder=True,
         ).to(device, dtype).eval()
 
         if strategy == "offload_to_cpu":