Ethanfel 505d445eb3 fix: wrap training loop in torch.enable_grad() ...

ComfyUI executes all nodes inside torch.no_grad(), which prevents gradient
tracking and makes loss.backward() fail. torch.enable_grad() overrides it.

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

2026-04-05 22:32:00 +02:00

..

__init__.py

feat: add SelVA LoRA Trainer ComfyUI node

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

selva_feature_extractor.py

fix: named .npz files always start at _001

2026-04-05 15:44:26 +02:00

selva_lora_loader.py

feat: LoRA fine-tuning for SelVA generator

2026-04-05 14:38:46 +02:00

selva_lora_trainer.py

fix: wrap training loop in torch.enable_grad()

2026-04-05 22:32:00 +02:00

selva_model_loader.py

feat: comprehensive node improvements

2026-04-04 18:16:03 +02:00

selva_sampler.py

fix: guarantee offload cleanup on exception with try/finally

2026-04-05 08:40:39 +02:00

utils.py

chore: remove all PrismAudio code from main branch

2026-04-04 17:58:31 +02:00