Ethanfel
f7a6f7790d
Modernized MisoTTS integration for ComfyUI with no torchtune/moshi: - vendored plain-torch Llama backbone (csm_llama), parity-verified Δ=0 vs torchtune - transformers.MimiModel codec (bit-identical codes to moshi), drops moshi/bnb/sphn - low-memory loader: streams 32GB fp32 checkpoint to GPU in bf16 (~18GB VRAM) - nodes: Model Loader, Generate (audiobook chunking + voice anchoring), EPUB Loader - pin-free requirements; runs on modern torch / Blackwell GPUs Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
16 lines
471 B
Python
16 lines
471 B
Python
from .nodes import MisoTTSModelLoader, MisoTTSGenerate, MisoTTSEpubLoader
|
|
|
|
NODE_CLASS_MAPPINGS = {
|
|
"MisoTTSModelLoader": MisoTTSModelLoader,
|
|
"MisoTTSGenerate": MisoTTSGenerate,
|
|
"MisoTTSEpubLoader": MisoTTSEpubLoader,
|
|
}
|
|
|
|
NODE_DISPLAY_NAME_MAPPINGS = {
|
|
"MisoTTSModelLoader": "MisoTTS Model Loader",
|
|
"MisoTTSGenerate": "MisoTTS Generate",
|
|
"MisoTTSEpubLoader": "MisoTTS EPUB Loader",
|
|
}
|
|
|
|
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
|