ComfyUI Node
MiniMax H3 Cast to Video (Extend)
A ComfyUI node in MiniMax H3/cast with 29 inputs and 4 outputs.
MiniMax H3 Cast to Video (Extend)
- clip
- vae
- context_latent
- audio_vae
- cast_1
- cast_2
- cast_3
- scene_images
- first_frame
- last_frame
- world_latent
- positive
- latent
- final_prompt
- report
◄prompt—►
◄length124►
◄max_views_per_member3►
◄auto_introtrue►
◄scene_description►
◄include_voicestrue►
◄context_frames2►
◄context_strength1.00►
◄context_static_timefalse►
◄pin_last_frametrue►
◄world_frames2►
◄world_strength1.00►
◄world_static_timefalse►
◄ref_image_sizematch►
◄ref_spacing1.0►
◄ref_strength1.00►
◄ref_decay0.00►
◄ref_ramp0.0►
CategoryMiniMax H3/cast
Inputs (29)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| vae | VAE | — | |
| context_latent | LATENT | AV latent output from a prior MiniMax H3 generation to continue from | |
| prompt | STRING | Refer to characters by NAME -- the <Picture i>/<Audio j> intro lines are written for you (see final_prompt output) | |
| 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. | |
| include_voicesopt | BOOLEAN | true | — |
| context_framesopt | INT | 21–64 | Trailing latent frames of context_latent carried over as context |
| context_strengthopt | FLOAT | 1.000–1 | — |
| context_static_timeopt | BOOLEAN | false | — |
| pin_last_frameopt | BOOLEAN | true | — |
| first_frameopt | IMAGE | Hard-pin this call's frame 0 (e.g. the prior clip's real last output frame) instead of pin_last_frame's decode | |
| last_frameopt | IMAGE | Pin this continuation segment's own final frame to an exact image, e.g. to land precisely on a known next shot/keyframe. Not supported by the fork's native MiniMaxH3VideoExtend -- silently dropped there (see report); supported when running against ComfyUI-MiniMax-H3-Extend's backport. | |
| world_latentopt | LATENT | — | |
| world_framesopt | INT | 21–64 | — |
| world_strengthopt | FLOAT | 1.000–1 | — |
| world_static_timeopt | BOOLEAN | false | — |
| 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 | — |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | — |
| latent | LATENT | — |
| final_prompt | STRING | — |
| report | STRING | — |