ComfyUI Node
PM LoRA Merger (Mergekit)
Core LoRA merger using Mergekit algorithms. Merges decomposed LoRA components using the selected merge method (TIES, DARE, SLERP, etc.). Processes layers in parallel using ThreadPoolExecutor for performance. Inputs: - method: Merge algorithm configuration from method nodes - components: Decomposed LoRA tensors from LoRA Decompose node - strengths: Per-LoRA weight multipliers (strength_model for UNet, strength_clip for CLIP) - lambda_: Global scaling factor applied to final merged result (0-1) - merge_clip: Whether to include CLIP layers in the merge (default: True) Outputs: - LoRABundle: Merged LoRA ready for application or saving - MergeContext: Reusable merge configuration for batch operations
PM LoRA Merger (Mergekit)
- method
- components
- strengths
- lora
- merge_context
◄lambda_1.00►
◄spectral_norm_scale0.00►
◄merge_cliptrue►
◄device▾►
◄dtype▾►
CategoryLoRA PowerMerge
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| method | MergeMethod | — | |
| components | LoRATensors | The decomposed components of the LoRAs to be merged. | |
| strengths | LoRAWeights | The weights of the LoRAs to be merged. | |
| lambda_ | FLOAT | 1.000–1 | Lambda value for scaling the merged model. |
| spectral_norm_scale | FLOAT | 0.000–100 | Spectral norm regularization. 0=disabled. >0=scale max Lipschitz constant to this value. Prevents any single layer from dominating due to large weight magnitudes. Common values: 0.5-2.0 (conservative), 1.0 (neutral), 2.0-5.0 (stronger effects). |
| merge_clip | BOOLEAN | true | Whether to merge CLIP (text encoder) layers. If False, CLIP layers are excluded from the output and LoRA Apply will not modify the CLIP model. |
| device | COMBO | 2 options: cuda, cpu | |
| dtype | COMBO | 3 options: float16, bfloat16, float32 |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| lora | LoRABundle | — |
| merge_context | MergeContext | — |