Nodes/HunyuanVideo-1.5 nodes/HunyuanVideo 1.5 Model Loader
ComfyUI Node

HunyuanVideo 1.5 Model Loader

A ComfyUI node in HunyuanVideoWrapper1.5 with 20 inputs and 1 output.

By yuanyuan-spec·Created 9 months ago·Updated 8 months ago· 27
HunyuanVideo 1.5 Model Loader
    • hunyuanvideo_model_config
    model_path
    attn_modeflash
    byt5_max_length256
    vision_encoder_typesiglip
    vision_encoder_precisionfp16
    text_encoder_typeqwen-2.5vl-7b
    text_encoder_tokenizer_typeqwen-2.5vl-7b
    text_encoder_max_length1000
    text_encoder_precisionfp16
    text_encoder_hidden_state_skip_layer2
    text_encoder_apply_final_normfalse
    text_encoder_reproducefalse
    resolution480p
    taskt2v
    enable_offloadingfalse
    enable_group_offloadingfalse
    transformer_dtypebfloat16
    device_optcuda
    hf_token
    flow_shift
    CategoryHunyuanVideoWrapper1.5

    Inputs (20)

    NameTypeDefaultDescription
    model_pathoptSTRING1. If you have already manually downloaded the model to your directory, specify the model folder path hyvideo-1.5 here. 2. If not specified, it will be automatically downloaded to the default folder for continued use.
    attn_modeoptCOMBOflash3 options: flash, ptm_sparse_attn, flash3
    byt5_max_lengthoptINT256
    vision_encoder_typeoptSTRINGsiglip
    vision_encoder_precisionoptSTRINGfp16
    text_encoder_typeoptSTRINGqwen-2.5vl-7b
    text_encoder_tokenizer_typeoptSTRINGqwen-2.5vl-7b
    text_encoder_max_lengthoptINT1000
    text_encoder_precisionoptSTRINGfp16
    text_encoder_hidden_state_skip_layeroptINT2
    text_encoder_apply_final_normoptBOOLEANfalse
    text_encoder_reproduceoptBOOLEANfalse
    resolutionoptCOMBO480p2 options: 480p, 720p
    taskoptCOMBOt2v2 options: t2v, i2v
    enable_offloadingoptBOOLEANfalse
    enable_group_offloadingoptBOOLEANfalse
    transformer_dtypeoptCOMBObfloat169 options: float32, float64, float16, bfloat16, uint8, int8, +3
    device_optoptCOMBOcuda2 options: cpu, cuda
    hf_tokenoptSTRING
    flow_shiftoptFLOATWhen the resolution is 480p, the recommended shift value is 5, and when the resolution is 720p, the recommended shift value is 7. If you do not set this value, it will be automatically configured according to the recommendations of this rule.

    Outputs (1)

    NameTypeDescription
    hunyuanvideo_model_configHUNYUANVIDEO_MODEL_CONFIG