Ethanfel
  • Joined on 2026-01-04
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-10 00:24:14 +02:00
187b2e3169 fix: cast GAFilter to model dtype after injection
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-10 00:18:06 +02:00
608746ce7b fix: cast input mel to model dtype before vocoder forward pass
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-10 00:17:17 +02:00
bba5aec7a5 fix: add CFG to LoRA mel pre-generation to match inference conditions
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-10 00:10:54 +02:00
d06936802b fix: cast mel_converter buffers to float32 to match STFT input dtype
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 23:53:47 +02:00
bee518a855 fix: cast all STFT inputs to float32 to prevent cuFFT bfloat16 crash
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 23:26:39 +02:00
48b72c0be0 feat: add LoRA mel pre-generation to BigVGAN vocoder trainer
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 22:07:32 +02:00
e16480b4c9 feat: add PiSSA/rsLoRA support to scheduler and PiSSA sweep experiment
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 21:54:38 +02:00
784fb2753f feat: PiSSA init, rsLoRA scaling, Spectral Surgery, and training fixes
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 20:28:57 +02:00
ecf828b007 fix: move vocoder to correct device after GAFilter injection
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 20:01:58 +02:00
793368af18 fix: strip inference flag before unnormalize in LoRA trainer eval
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 19:36:06 +02:00
1d1ae61409 fix: move only VAE+vocoder to GPU during eval to prevent device mismatch
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:57:12 +02:00
8fa2699551 fix: correct DITTO reference latent space mismatch
Ethanfel pushed to master at Ethanfel/Comfyui-Nodes-Stats 2026-04-09 18:47:18 +02:00
4ccc772bb9 chore: bump version to 1.1.0
Ethanfel pushed to master at Ethanfel/Comfyui-Nodes-Stats 2026-04-09 18:43:25 +02:00
777e4890ae docs: update README for model tracking feature
9477777124 fix: scope input-scanning loop inside per-node try/except in extract_models_from_prompt
831ed302e9 fix: update model_type on upsert conflict and scope close button to dialog
c7003df0bb fix: scope badge querySelector to dialog, update dialog title
bf5c8683a7 feat: add Models tab with per-type usage stats
Compare 16 commits »
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:40:22 +02:00
14fabf01f9 fix: reduce opt_lr step to 0.001 to allow finer lr control in DITTO
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:30:07 +02:00
445da1e69b fix: replace std clamp with anchor regularization to prevent OOD noise
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:23:41 +02:00
fa6c4fa834 fix: clamp x0 std after each optimizer step to prevent OOD noise
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:18:42 +02:00
286681edff fix: cast mel to model dtype before VAE encode in DITTO reference loading
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:15:29 +02:00
056a7b973d fix: enable VAE encoder in model loader — required for DITTO reference encoding
Ethanfel pushed to feature/lora-timestep-sampling at Ethanfel/ComfyUI-SelVA 2026-04-09 18:12:33 +02:00
633fe36fbb fix: compute DITTO style loss in latent space to eliminate VAE decoder noise