ComfyUI Node
MiniMax H3 Generation V2 (Acceleration + Clean Decode)
A ComfyUI node in IAMCCS/MiniMax H3/Atomic Backend with 16 inputs and 6 outputs.
MiniMax H3 Generation V2 (Acceleration + Clean Decode)
- model
- positive
- latent
- video_vae
- audio_vae
- cine_linx
- motion_state
- native_frames
- native_audio
- bridge_last_frame
- sampled_latent
- native_fps
- report
◄chunk_index—►
◄seed42►
◄seed_stride1►
◄steps20►
◄sampler_name▾►
◄scheduler▾►
◄denoise1.00►
◄shift_video12.00►
◄shift_audio3.00►
CategoryIAMCCS/MiniMax H3/Atomic Backend
Inputs (16)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| positive | CONDITIONING | — | |
| latent | LATENT | — | |
| video_vae | VAE | — | |
| audio_vae | VAE | — | |
| cine_linx | IAMCCS_SUPERNODE_LINX | — | |
| chunk_index | INT | — | |
| seed | INT | 420–18446744073709550000 | — |
| seed_stride | INT | 10–18446744073709550000 | — |
| steps | INT | 201–100 | — |
| sampler_name | COMBO | 44 options: res_multistep, euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, +38 | |
| scheduler | COMBO | 9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3 | |
| denoise | FLOAT | 1.000–1 | — |
| shift_video | FLOAT | 12.000.01–100 | — |
| shift_audio | FLOAT | 3.000.01–100 | — |
| motion_stateopt | IAMCCS_H3_MOTION_CONTEXT | — |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| native_frames | IMAGE | — |
| native_audio | AUDIO | — |
| bridge_last_frame | IMAGE | — |
| sampled_latent | LATENT | — |
| native_fps | INT | — |
| report | STRING | — |