ComfyUI-SelVA

Files

T

EthanfelandClaude Sonnet 4.6 3d9221c248 fix: three bugs in scheduler and trainer

- trainer: raise ValueError early when remaining steps < log_interval (50)
  instead of UnboundLocalError on smoothed_img/final_path at return
- trainer: use None in grad_norm_history instead of silent 0.0 when
  grad_accum > log_interval and no optimizer step fired in the interval
- trainer: include start_step in _train_inner return dict
- scheduler: use start_step from result dict for min_loss_step and
  loss_at_steps (fixes wrong step labels on resumed experiments)

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

2026-04-06 13:11:25 +02:00

__init__.py

feat: add SelVA LoRA Scheduler node for automated experiment sweeps

2026-04-06 13:03:21 +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_scheduler.py

fix: three bugs in scheduler and trainer