Ethanfel 10a71b0c4f fix: offload entire model to CPU in main thread before worker starts ...

The previous offload ran inside the worker thread, but by then ComfyUI
had already loaded the full model to GPU. Now feature_utils.to('cpu')
and generator.to('cpu') run in the main thread right after
unload_all_models(), before the worker starts. vocoder.to(device, dtype)
is called explicitly after inference flag stripping in _do_train to
bring only the vocoder back to GPU.

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

2026-04-10 00:56:13 +02:00

..

__init__.py

fix: remove FlashSR (audiosr incompatible with Python 3.12), add training loss CSV

2026-04-09 17:18:34 +02:00

selva_activation_steering_extractor.py

feat(steering): conditional-only injection + per-position vectors

2026-04-09 01:02:51 +02:00

selva_activation_steering_loader.py

feat: add activation steering pipeline (extractor, loader, sampler injection)

2026-04-09 00:38:26 +02:00

selva_audio_postprocess.py

fix: remove FlashSR (audiosr incompatible with Python 3.12), add training loss CSV

2026-04-09 17:18:34 +02:00

selva_audio_preprocessors.py

feat: add SelVA HF Smoother and Spectral Matcher preprocessing nodes

2026-04-08 20:28:16 +02:00

selva_bigvgan_loader.py

fix: move vocoder to correct device after GAFilter injection

2026-04-09 20:28:55 +02:00

selva_bigvgan_trainer.py

fix: offload entire model to CPU in main thread before worker starts

2026-04-10 00:56:13 +02:00

selva_dataset_browser.py

feat: thorough overnight sweep + dataset browser updates

2026-04-08 00:38:19 +02:00

selva_dataset_pipeline.py

feat: add SelvaDatasetCompressor node for parallel compression

2026-04-09 15:36:27 +02:00

selva_ditto_optimizer.py

fix: correct DITTO reference latent space mismatch

2026-04-09 18:57:08 +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_evaluator.py

feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes

2026-04-09 21:54:36 +02:00

selva_lora_loader.py

feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes

2026-04-09 21:54:36 +02:00

selva_lora_scheduler.py

feat: add PiSSA/rsLoRA support to scheduler and PiSSA sweep experiment

2026-04-09 22:07:27 +02:00

selva_lora_trainer.py

feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes

2026-04-09 21:54:36 +02:00

selva_model_loader.py

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

2026-04-09 18:15:27 +02:00

selva_sampler.py

feat(steering): conditional-only injection + per-position vectors

2026-04-09 01:02:51 +02:00

selva_skip_experiment.py

feat: SelVA Skip Experiment node + save partial scalars on skip

2026-04-08 13:10:43 +02:00

selva_textual_inversion_loader.py

feat: add inject_mode (suffix/prefix) to TI pipeline

2026-04-08 23:31:52 +02:00

selva_textual_inversion_trainer.py

fix: move only VAE+vocoder to GPU during eval to prevent device mismatch

2026-04-09 19:36:02 +02:00

selva_ti_scheduler.py

fix(ti): lower default lr/batch, add lr_batch sweep group

2026-04-08 23:42:22 +02:00

selva_vae_roundtrip.py

fix: move only VAE+vocoder to GPU during eval to prevent device mismatch

2026-04-09 19:36:02 +02:00

utils.py

chore: remove all PrismAudio code from main branch

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