ComfyUI Node
FL MiniMax H3 LoRA Block Loader
Load one H3 LoRA with per-block strengths. Only this adapter is scaled; existing model patches are preserved. All multipliers at 1 match normal model-only LoRA loading.
FL MiniMax H3 LoRA Block Loader
- model
- model
- block_report
◄lora_name▾►
◄strength_model1.00►
◄blocks_strength1.00►
◄refiner_strength1.00►
◄other_strength1.00►
◄block_overrides►
CategoryFL/MiniMax H3/Model
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| lora_name | COMBO | 0 options: | |
| strength_model | FLOAT | 1.00-10–10 | — |
| blocks_strength | FLOAT | 1.00-10–10 | Multiplier for main transformer blocks. |
| refiner_strength | FLOAT | 1.00-10–10 | Multiplier for token-refiner blocks; not the external Qwen encoder. |
| other_strength | FLOAT | 1.00-10–10 | Multiplier for adapter targets outside both stacks: projections, time embedding and final layer. |
| block_overrides | STRING | One rule per line: blocks.0-9=0.5 or refiner.1=0. Zero-based, inclusive ranges. Replaces the group multiplier; overall strength still applies. Later rules win. # comments allowed. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| block_report | STRING | — |