ComfyUI Node
HunyuanVideo Sr Transformer
A ComfyUI node in HunyuanVideoWrapper1.5 with 14 inputs and 1 output.
HunyuanVideo Sr Transformer
- hyvid_cfg
- transformer
- vae_concat
- hyvid_embeds
- vision_states
- extra_kwargs
- lantens_dict
- latent
◄target_dtypebfloat16►
◄n_tokens1►
◄steps8►
◄embedded_guidance_scale—►
◄autocast_enabledtrue►
◄eta0.00►
◄guidance_rescale0.00►
CategoryHunyuanVideoWrapper1.5
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| hyvid_cfg | HYVID15CFG | — | |
| target_dtype | COMBO | bfloat16 | 9 options: float32, float64, float16, bfloat16, uint8, int8, +3 |
| n_tokens | INT | 11–1000 | — |
| steps | INT | 81–1000 | — |
| transformer | HYVID15TRANSFORMER | — | |
| vae_concat | HYVID15VAECONCAT | — | |
| hyvid_embeds | HYVIDEMBEDS | — | |
| vision_states | HYVID15VISIONSTATES | — | |
| extra_kwargs | HYVID15EXTRAKWARGS | — | |
| lantens_dict | HYVID15LATENTSDICT | — | |
| embedded_guidance_scaleopt | FLOAT | 0–10 | — |
| autocast_enabledopt | BOOLEAN | true | — |
| etaopt | FLOAT | 0.000–1 | — |
| guidance_rescaleopt | FLOAT | 0.00 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| latent | HYVID15TRANSFORMERLATENT | — |