ComfyUI-SelVA

Files

T

Ethanfel 849f31e2a6 fix: create LoRA params inside torch.enable_grad() to escape inference_mode

torch.enable_grad() re-enables grad tracking but nn.Parameters created while
torch.inference_mode() is active are inference tensors that can't enter autograd
regardless. Splitting into _train_inner() and calling it inside enable_grad()
ensures the deepcopy, apply_lora, and the training loop all run with a clean
autograd context.

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

2026-04-05 22:36:28 +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: create LoRA params inside torch.enable_grad() to escape inference_mode