Nodes/ComfyUI-GGUF-Loader/Scenema Models Loader ⚡
ComfyUI Node

Scenema Models Loader ⚡

Load the Scenema Audio components (audio DiT, Gemma-3 text encoder with GGUF support, audio VAE) as native comfy objects.

By ChrisColeTech·Created 13 days ago·Updated about 3 hours ago· 6
Scenema Models Loader ⚡
    • model
    • clip
    • vae
    transformer_name
    text_encoder_name
    pipeline_name
    vae_encoder_name
    keep_loadedtrue
    Category🤖 CCTech/Scenema

    Inputs (5)

    NameTypeDefaultDescription
    transformer_nameCOMBOscenema-audio-transformer-int8.safetensors (or the bf16 checkpoint, or a GGUF quant of either) from models/diffusion_models (unet). INT8 and GGUF weights remain quantized and dequantize one layer at a time.
    text_encoder_nameCOMBOGemma-3 12B text encoder, .gguf (stays quantized) or safetensors, from models/text_encoders (clip).
    pipeline_nameCOMBOscenema-audio-pipeline.safetensors (or -pipeline-audio) from models/vae. Carries the text projection, embeddings connectors, audio VAE decoder and vocoder.
    vae_encoder_nameCOMBOscenema-audio-vae-encoder.safetensors from models/vae. Optional: needed to encode voice references only when the pipeline file above ships without its encoder (the full pipeline checkpoint already includes one).
    keep_loadedBOOLEANtrueReuse the last-built model/clip/vae when these four filenames are unchanged, instead of rebuilding from disk every run (the DiT alone is 7-10 GB, the text encoder ~24 GB). Turn off to always force a fresh rebuild, e.g. after replacing a file on disk without renaming it.

    Outputs (3)

    NameTypeDescription
    modelMODEL
    clipCLIP
    vaeVAE