ComfyUI-SelVA

Files

T

Ethanfel d83632e754 fix: pad/trim clip and sync features to fixed seq_len at dataset load time

Clips from shorter videos produce fewer CLIP frames (e.g. 2s → 16 frames,
8s → 64 frames). Mixed-length datasets would cause torch.stack() to fail
during batching. Normalize to seq_cfg.clip_seq_len / sync_seq_len at load,
same as latents are already normalized to latent_seq_len.

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

2026-04-06 00:54:05 +02:00

__init__.py

feat: add SelVA LoRA Trainer ComfyUI node

2026-04-05 17:07:38 +02:00

selva_feature_extractor.py

fix: set OUTPUT_NODE=True on SelVA Feature Extractor so it runs without connected outputs

2026-04-06 00:11:16 +02:00

selva_lora_loader.py

debug: print lora_A norm after loading to confirm adapter applied

2026-04-05 23:05:23 +02:00

selva_lora_trainer.py

fix: pad/trim clip and sync features to fixed seq_len at dataset load time