ComfyUI Node
HunyuanVideo Transformer
A ComfyUI node in HunyuanVideoWrapper1.5 with 21 inputs and 1 output.
HunyuanVideo Transformer
- hyvid_cfg
- transformer
- vae_concat
- hyvid_embeds
- vision_states
- extra_kwargs
- latents_dict
- transformer_latent
◄n_tokens1►
◄steps50►
◄target_dtypebfloat16►
◄embedded_guidance_scale—►
◄guidance_rescale0.00►
◄autocast_enabledtrue►
◄eta0.00►
◄enable_cachefalse►
◄cache_start_step11►
◄cache_end_step45►
◄no_cache_block_id53►
◄cache_step_interval4►
◄cache_typedeepcache►
◄enable_sageattnfalse►
CategoryHunyuanVideoWrapper1.5
Inputs (21)
| Name | Type | Default | Description |
|---|---|---|---|
| hyvid_cfg | HYVID15CFG | — | |
| n_tokens | INT | 11–1000 | — |
| steps | INT | 501–1000 | — |
| transformer | HYVID15TRANSFORMER | — | |
| vae_concat | HYVID15VAECONCAT | — | |
| hyvid_embeds | HYVIDEMBEDS | — | |
| vision_states | HYVID15VISIONSTATES | — | |
| extra_kwargs | HYVID15EXTRAKWARGS | — | |
| latents_dict | HYVID15LATENTSDICT | — | |
| target_dtype | COMBO | bfloat16 | 9 options: float32, float64, float16, bfloat16, uint8, int8, +3 |
| embedded_guidance_scaleopt | FLOAT | Additional control guidance scale, if supported | |
| guidance_rescaleopt | FLOAT | 0.00 | — |
| autocast_enabledopt | BOOLEAN | true | — |
| etaopt | FLOAT | 0.000–1 | — |
| enable_cacheopt | BOOLEAN | false | Enable cache. |
| cache_start_stepopt | INT | 11 | Cache start step. |
| cache_end_stepopt | INT | 45 | Cache end step. |
| no_cache_block_idopt | INT | 53 | No cache block id. |
| cache_step_intervalopt | INT | 4 | Cache step interval. |
| cache_typeopt | COMBO | deepcache | Cache type. |
| enable_sageattnopt | BOOLEAN | false | Enable sageattn. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| transformer_latent | HYVID15TRANSFORMERLATENT | — |