Ethanfel/ComfyUI-SelVA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
170 Commits 6 Branches 0 Tags
10e6095e3196c3242880cb59d4e72f55de322374
Commit Graph

170 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ethanfel afc7d5b657 fix: add missing runtime dependencies to requirements.txt 
einops-exts, vector-quantize-pytorch, scipy were imported by prismaudio_core
but not listed in requirements.txt.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 19:48:33 +01:00
Ethanfel e372cdc488 fix: add plugin root to sys.path so prismaudio_core is importable 
ComfyUI does not add the custom node directory to sys.path automatically,
so prismaudio_core (a package inside the plugin dir) was not found at runtime.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 19:41:11 +01:00
Ethanfel 7671d296fa fix: remove spurious caption_cot input entry from video_to_audio workflow 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 19:39:05 +01:00
Ethanfel 3894fcc9b4 feat: add demo workflows for text-to-audio and video-to-audio 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 19:32:24 +01:00
Ethanfel 35d0615253 feat: auto-install pip venv for feature extraction on first use 
PrismAudioFeatureExtractor now creates and populates a managed venv
(_extract_env/) automatically when python_env is left as the default
'python'. Also adds scripts/install_extract_env.sh for manual/Docker
setup without conda.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 19:27:27 +01:00
Ethanfel 9b1cb71b2a fix: remove MMDiTWrapper import and dead code paths from factory.py 
MMDiTWrapper was removed from diffusion.py during cleanup but the import
in factory.py was missed, causing ImportError on every model load.
Also stub wavelet and diffusion_prior paths that reference deleted modules.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 19:12:40 +01:00
Ethanfel 807f00417f docs: README with installation and usage instructions 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:15:17 +01:00
Ethanfel 618e7de64b feat: PrismAudioTextOnly node with correct T5-Gemma encoding 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:09:11 +01:00
Ethanfel 3d62688e8c feat: PrismAudioSampler node with correct metadata format and peak normalization 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:07:33 +01:00
Ethanfel 7c54ee8482 feat: PrismAudioFeatureExtractor node with subprocess bridge and conda env 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:06:10 +01:00
Ethanfel 3f35aa39f2 feat: PrismAudioFeatureLoader node for pre-computed .npz files 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:04:32 +01:00
Ethanfel 1043f4bacb feat: PrismAudioModelLoader node with auto-download and adaptive VRAM 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:02:47 +01:00
Ethanfel 8b634923dd fix: remove unused tqdm import from sampling.py 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 18:01:29 +01:00
Ethanfel 87bea21d49 feat: extract prismaudio_core inference with callback-enabled sampling 
Add inference subpackage with:
- sampling.py: sample_discrete_euler modified from upstream to add callback
  parameter for ComfyUI progress bars (uses enumerate for step index)
- utils.py: set_audio_channels and prepare_audio for audio preprocessing

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-27 17:59:37 +01:00
Ethanfel 30e85f0f99 fix: resolve critical bugs and quality issues in prismaudio_core/models 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-27 17:56:02 +01:00
Ethanfel 6e1186d5bd fix: clean up dead code paths and debug artifacts in prismaudio_core/models 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-27 17:49:57 +01:00
Ethanfel 84c81e0e55 feat: extract prismaudio_core model modules (DiT, conditioners, VAE, diffusion) 
Fetch and adapt inference-critical model modules from upstream PrismAudio repo:
- dit.py: DiffusionTransformer with debug prints removed
- diffusion.py: ConditionedDiffusionModelWrapper, DiTWrapper, MMDiTWrapper
- conditioners.py: Cond_MLP, Sync_MLP, MultiConditioner with stubbed training imports
- autoencoders.py: AudioAutoencoder, OobleckEncoder/Decoder
- transformer.py: ContinuousTransformer, Attention with flash_attn fallback to SDPA
- blocks.py, utils.py, bottleneck.py, pretransforms.py, local_attention.py, pqmf.py
- adp.py: UNetCFG1d, UNet1d, NumberEmbedder
- mmmodules/model/low_level.py: MLP, ChannelLastConv1d, ConvMLP

All internal imports rewritten from PrismAudio.* to prismaudio_core.*,
training-only imports stubbed, flash_attn made optional with HAS_FLASH_ATTN flag.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-27 17:31:22 +01:00
Ethanfel b60ff4111b feat: extract prismaudio_core config and model factory 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-27 17:05:57 +01:00
Ethanfel baa80de194 feat: project scaffolding with shared utils and node registration 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-27 16:59:21 +01:00
Ethanfel c9364c4ec2 docs: initial design and implementation plan 2026-03-27 16:57:15 +01:00