ComfyUI Node
Krea2 SVDQuant LoRA Loader
Applies a LoRA to a Krea2 W4A4 quantized model as a parallel low-rank branch, leaving the 4-bit weight untouched. The stock loader has to dequantize, add and requantize, which puts the LoRA delta through 4-bit quantization along with the weight. LoKr/LoHa/OFT cannot fold into the branch and run per-forward instead; the 'adapters' input trades that exactness back for the stock loader's speed.
Krea2 SVDQuant LoRA Loader
- model
- model
◄lora_name▾►
◄strength1.00►
◄adaptersbypass (exact, slower)►
CategoryKrea2/SVDQuant
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | Output of the Krea2 SVDQuant W4A4 Loader, or any Krea2 checkpoint with convrot_w4a4 quantized blocks. | |
| lora_name | COMBO | A Krea2 LoRA. Targets 'blocks.N.{attn,mlp}.*' under either prefix ('diffusion_model.' or 'transformer.') for the quantized blocks; anything else it carries (txtfusion etc.) goes through ComfyUI's normal path. | |
| strength | FLOAT | 1.00-10–10 | 0 passes the model through untouched. Negative values invert the LoRA. Chain more of these nodes to stack LoRAs - the whole stack is rebuilt each time, so strengths stay exact. |
| adaptersopt | COMBO | bypass (exact, slower) | Only affects LoRAs that cannot fold directly into the low-rank branch (LoKr, LoHa, OFT); a plain LoRA is free in all modes. 'bypass' computes the adapter every forward without touching the 4-bit weight. 'svd delta' decomposes the delta into low-rank factors (zero per-step overhead). 'bake' rewrites the weight once: fast, but quantizes the delta to 4 bits. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| model | MODEL | The model with the LoRA attached as a parallel branch. |