Nodes/ComfyUI-Tween/Load LDF-VFI Model
ComfyUI Node

Load LDF-VFI Model

A ComfyUI node in video/LDF-VFI with 5 inputs and 1 output.

By ethanfel·Created 6 months ago·Updated 10 days ago· 14
Load LDF-VFI Model
    • model
    modelonecat-ai/LDF-VFI
    tile_size256
    tile_overlap64
    vae_batch_size8
    attention_typeslide_chunk_all_block_2x1x1
    Categoryvideo/LDF-VFI

    Inputs (5)

    NameTypeDefaultDescription
    modelCOMBOonecat-ai/LDF-VFIOfficial LDF-VFI transformer + conditional VAE. Downloads ~6.4 GB on first use and needs about 20 GB VRAM.
    tile_sizeINT256128–1024Spatial VAE tile size. Larger tiles can improve throughput but use more VRAM.
    tile_overlapINT648–512Spatial overlap blended between VAE tiles. Must be smaller than tile_size.
    vae_batch_sizeINT81–32VAE temporal-tile batch size. Lower this first if VAE encoding or decoding runs out of VRAM.
    attention_typeCOMBOslide_chunk_all_block_2x1x1Official quick-start sparse attention is recommended. Full attention is extremely memory-intensive.

    Outputs (1)

    NameTypeDescription
    modelLDF_VFI_MODEL