ComfyUI Node: HunyuanVideo 1.5 Model Loader
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
model_path STRING
attn_mode
- flash
- ptm_sparse_attn
- flash3
byt5_max_length INT
vision_encoder_type STRING
vision_encoder_precision STRING
text_encoder_type STRING
text_encoder_tokenizer_type STRING
text_encoder_max_length INT
text_encoder_precision STRING
text_encoder_hidden_state_skip_layer INT
text_encoder_apply_final_norm BOOLEAN
text_encoder_reproduce BOOLEAN
resolution
- 480p
- 720p
task
- t2v
- i2v
enable_offloading BOOLEAN
enable_group_offloading BOOLEAN
transformer_dtype
- float32
- float64
- float16
- bfloat16
- uint8
- int8
- int16
- int32
- int64
device_opt
- cpu
- cuda
hf_token STRING
flow_shift FLOAT
Outputs
HUNYUANVIDEO_MODEL_CONFIG
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
Looking for a different node?
More nodes in HunyuanVideo-1.5 nodes
- HyVidelSrTransformerUpsamplerLoader
- HyVidelSrVaeDecoder
- HunyuanVideo byt5 loader
- HunyuanVideo CFG
- HunyuanVideo Glyph by T5
- HunyuanVideo 1.5 Leo Image-to-Video Sampler
- HunyuanVideo Prepare Latents
- HunyuanVideo 1.5 Leo Text-to-Video Sampler
- HunyuanVideo text encode
- HunyuanVideo 1.5 Leo Text Encoder Model Loader
- HunyuanVideo Transformer
- HunyuanVideo 1.5 Leo Transformer Model Loader
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.