Ethanfel
  • Joined on 2026-01-04
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 15:35:23 +02:00
5366f6992e feat: add tooltips with inline tag reference to generator node inputs
Ethanfel pushed to feature/lora-training at Ethanfel/ComfyUI-SelVA 2026-04-05 15:30:26 +02:00
c88e27742c fix: sanitize name field and remove double load_npz call
Ethanfel pushed to feature/lora-training at Ethanfel/ComfyUI-SelVA 2026-04-05 15:16:52 +02:00
cbcd154c96 feat: add name field with auto-increment to SelvaFeatureExtractor
Ethanfel pushed to feature/lora-training at Ethanfel/ComfyUI-SelVA 2026-04-05 15:14:31 +02:00
1eb82d8050 refactor: train_lora accepts .npz + audio pairs instead of raw video
Ethanfel pushed to feature/lora-training at Ethanfel/ComfyUI-SelVA 2026-04-05 14:57:30 +02:00
cde280049b fix: correct LoRALinear dtype and remove unused import
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 14:53:34 +02:00
f647a24988 fix: add install.py to prevent omnivoice from overwriting ComfyUI's torch
Ethanfel created branch feature/lora-training in Ethanfel/ComfyUI-SelVA 2026-04-05 14:38:47 +02:00
Ethanfel pushed to feature/lora-training at Ethanfel/ComfyUI-SelVA 2026-04-05 14:38:47 +02:00
437c62b28f feat: LoRA fine-tuning for SelVA generator
Ethanfel pushed to experiment/crop-to-mask at Ethanfel/ComfyUI-SelVA 2026-04-05 13:04:48 +02:00
c9550ce693 experiment: add crop_rect option — rect bbox crop without squarification
Ethanfel created branch experiment/crop-to-mask in Ethanfel/ComfyUI-SelVA 2026-04-05 12:52:07 +02:00
Ethanfel pushed to experiment/crop-to-mask at Ethanfel/ComfyUI-SelVA 2026-04-05 12:52:07 +02:00
f3cabcad90 experiment: crop-to-mask mode on feature extractor
Ethanfel pushed to main at Ethanfel/ComfyUI-SelVA 2026-04-05 10:43:44 +02:00
b519b042e2 docs: document mask inputs and normalize toggle in README
Ethanfel pushed to main at Ethanfel/ComfyUI-SelVA 2026-04-05 10:43:07 +02:00
f28759f1e3 feat: improve mask support with neutral fill, mask_strength, and per-path toggles
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:41:09 +02:00
b273f8f2d7 refactor: remove redundant condition and rename shadowed waveform variable
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:39:46 +02:00
0760e60373 chore: remove torch/torchaudio from requirements (omnivoice declares them)
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:38:39 +02:00
0ffd624471 fix: protect os.unlink in finally block from masking original exceptions
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:34:54 +02:00
a2c542a2bc fix: move output waveform to CPU and cast sample_rate to int
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:31:43 +02:00
49b1ee5c16 docs: add README
Ethanfel created branch master in Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:29:34 +02:00
Ethanfel pushed to master at Ethanfel/ComfyUI-Omnivoice 2026-04-05 10:29:34 +02:00
808580b771 fix: guard omnivoice import in loader.py so node classes are importable without package
18fe6359cf fix: add input validation and cpu() guard in OmniVoiceGenerate
95712e5504 feat: add OmniVoiceGenerate node with voice cloning, design, and auto modes
7e94733b21 docs: document private pytest API usage in conftest
11beba1c47 fix: clean up omnivoice import guard and __init__ error masking