ComfyUI Node
MiniMax H3 Cast to Video
A ComfyUI node in MiniMax H3/cast with 21 inputs and 4 outputs.
MiniMax H3 Cast to Video
- clip
- vae
- audio_vae
- cast_1
- cast_2
- cast_3
- scene_images
- positive
- latent
- final_prompt
- report
◄prompt—►
◄width1344►
◄height768►
◄length124►
◄max_views_per_member3►
◄auto_introtrue►
◄scene_description►
◄include_voicestrue►
◄ref_image_sizematch►
◄ref_spacing1.0►
◄ref_strength1.00►
◄ref_decay0.00►
◄ref_ramp0.0►
◄temporal_stretch1.0►
CategoryMiniMax H3/cast
Inputs (21)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| vae | VAE | — | |
| prompt | STRING | Refer to characters by NAME -- the <Picture i>/<Audio j> intro lines are written for you (see final_prompt output) | |
| width | INT | 134432–8192 | — |
| height | INT | 76832–8192 | — |
| length | INT | 1245–3600 | — |
| max_views_per_member | INT | 31–9 | Views taken per cast member, in saved order. 9 total image slots are shared by all members + scene images. |
| auto_intro | BOOLEAN | true | Write the '<Picture 1>, <Picture 2>: Name -- description' intro lines automatically |
| audio_vaeopt | VAE | — | |
| cast_1opt | H3_CAST_MEMBER | — | |
| cast_2opt | H3_CAST_MEMBER | — | |
| cast_3opt | H3_CAST_MEMBER | — | |
| scene_imagesopt | IMAGE | Extra reference images of the location/scene (e.g. room renders); batch = one ref slot per frame | |
| scene_descriptionopt | STRING | What's actually in scene_images -- used verbatim in the intro line instead of the generic 'the location where this scene takes place.' placeholder. Concrete detail here (like Plan v2's Image Reference description) is what actually anchors the model to the background; leave blank only if you want the old generic behavior. | |
| include_voicesopt | BOOLEAN | true | — |
| ref_image_sizeopt | COMBO | match | 2 options: match, max |
| ref_spacingopt | FLOAT | 1.00–50 | — |
| ref_strengthopt | FLOAT | 1.000–1 | — |
| ref_decayopt | FLOAT | 0.000–1 | — |
| ref_rampopt | FLOAT | 0.00–50 | — |
| temporal_stretchopt | FLOAT | 1.01–100 | — |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| latent | LATENT | — |
| final_prompt | STRING | — |
| report | STRING | — |