ComfyUI Node
Krea2T Character LoRA — Image Only
Applies a Krea2 character LoRA directly to image tokens and skips unsupported weights. Use in place of the regular loader for that character. Other LoRAs remain active. Text and image still interact through the model's normal attention.
Krea2T Character LoRA — Image Only
- model
- model
- report
◄lora_name▾►
◄strength_model1.00►
◄enabledtrue►
CategoryKrea2/loaders
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | — | |
| lora_name | COMBO | Character LoRA. Loads canonical A/B pairs for Krea2's shared DiT attention and MLP projections; other keys are skipped. | |
| strength_model | FLOAT | 1.00-100–100 | Strength of this character adapter on image-token rows. Text-token rows receive no direct contribution from this adapter. |
| enabled | BOOLEAN | true | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| report | STRING | — |