Nodes/ComfyUI_Wan2_1_lora_trainer/Musubi Sampling Settings (Wan)
ComfyUI Node

Musubi Sampling Settings (Wan)

A ComfyUI node in musubi-tuner/wan/settings with 7 inputs and 1 output.

By jaimitoes·Created about a year ago·Updated 12 months ago· 61
Musubi Sampling Settings (Wan)
    • sampling_settings
    sample_every_n_steps0
    sample_every_n_epochs0
    sample_at_firsttrue
    vae_name
    t5_name
    clip_nameNone
    prompts_texta beautiful sunset over mountains
    Categorymusubi-tuner/wan/settings

    Inputs (7)

    NameTypeDefaultDescription
    sample_every_n_stepsINT0Generate a sample every n steps.
    sample_every_n_epochsINT0Generate a sample every n epoch.
    sample_at_firstBOOLEANtrueGenera a sample at the starting training.
    vae_nameCOMBOThe same vae used to caching
    t5_nameCOMBOThe same T5 used to caching
    clip_nameCOMBONoneIf I2V, the same clip vision used for caching
    prompts_textSTRINGa beautiful sunset over mountainsWrite a prompt. You can specify width and height by using --w --h. Example : a cat making surf --w 832 --h 480

    Outputs (1)

    NameTypeDescription
    sampling_settingsDICT