ComfyUI Node: HunyuanVideo Transformer

Authored by yuanyuan-spec

Created

Updated

27 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

HunyuanVideoWrapper1.5

Inputs

hyvid_cfg HYVID15CFG
n_tokens INT
steps INT
transformer HYVID15TRANSFORMER
vae_concat HYVID15VAECONCAT
hyvid_embeds HYVIDEMBEDS
vision_states HYVID15VISIONSTATES
extra_kwargs HYVID15EXTRAKWARGS
latents_dict HYVID15LATENTSDICT
target_dtype
  • float32
  • float64
  • float16
  • bfloat16
  • uint8
  • int8
  • int16
  • int32
  • int64
embedded_guidance_scale FLOAT
guidance_rescale FLOAT
autocast_enabled BOOLEAN
eta FLOAT
enable_cache BOOLEAN
cache_start_step INT
cache_end_step INT
no_cache_block_id INT
cache_step_interval INT
cache_type
  • deepcache
  • teacache
  • taylorcache
enable_sageattn BOOLEAN

Outputs

HYVID15TRANSFORMERLATENT

Extension: HunyuanVideo-1.5 nodes

A ComfyUI plugin based on HunyuanVideo-1.5, offering both simplified and complete node sets for quick usage or deep workflow customization.

Authored by yuanyuan-spec

View Nodes

Looking for a different node?

More nodes in HunyuanVideo-1.5 nodes

Other HunyuanVideoWrapper1.5 nodes

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more