ComfyUI Node
MiniMax H3 Temporal LoRA Blend
Different LoRA weights before/after a moment IN THE CLIP. Each sampling step runs both models' predictions and blends them along the video timeline with a feathered ramp — one coherent motion trajectory, LoRA influence changing at your chosen second. Wire model_base straight from the checkpoint loader, branch your LoRA loaders off it for model_a (used BEFORE the boundary) and model_b (AFTER; leave empty to drop to the clean base). All three must come from the SAME loaded checkpoint. Costs ~2x sampling time and one extra VRAM copy of the LoRA-touched weights. Needs the model fully resident (no lowvram streaming). Do NOT put the turbo/distill LoRA on only one side — both sides must expect the same sigma schedule.
MiniMax H3 Temporal LoRA Blend
- model_base
- model_a
- model_b
- MODEL
◄boundary_seconds2.0►
◄feather_seconds0.5►
◄audio_fromramp►
Categorymodel/minimax
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| model_base | MODEL | The shared checkpoint, WITHOUT the time-windowed LoRAs. Sampler loads this state. | |
| model_a | MODEL | Used BEFORE boundary_seconds. Usually model_base -> LoRA loader(s). | |
| boundary_seconds | FLOAT | 2.00–20 | Clip time where influence hands over from model_a to model_b. |
| feather_seconds | FLOAT | 0.50–10 | Width of the linear cross-blend centred on the boundary. 0 = hard switch between adjacent latent frames. |
| audio_from | COMBO | ramp | H3 generates audio jointly. 'ramp' blends the audio stream on the same time curve; or pin the whole soundtrack's prediction to one side. |
| model_bopt | MODEL | Used AFTER boundary_seconds. Empty = the clean base (i.e. the LoRA is dropped at the boundary). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| MODEL | MODEL | Wrapped model — feed this to the sampler. |