Intrinsic Lora Sampling

KJNodes

Intrinsic_lora_sampling

Sampler to use the intrinsic loras: https://github.com/duxiaodan/intrinsic-lora These LoRAs are tiny and thus included with this node pack.

Example

JSON Example

{
  "class_type": "Intrinsic_lora_sampling",
  "inputs": {
    "model": [
      "node_id",
      0
    ],
    "lora_name": "https://civitai.com/api/download/models/123456?type=Model&format=SafeTensor",
    "task": "depth map",
    "text": "",
    "clip": [
      "node_id",
      0
    ],
    "vae": [
      "node_id",
      0
    ],
    "per_batch": 16
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

Name	Type	Status	Constraints	Default
model	MODEL	required	-	-
lora_name	ENUM 5 options intrinsic_lora_sd15_albedo.safetensors intrinsic_lora_sd15_depth.safetensors intrinsic_lora_sd15_normal.safetensors intrinsic_lora_sd15_shading.safetensors intrinsic_loras.txt URL: LoRA	required	-	-
task	ENUM 4 options depth map surface normals albedo shading	required	-	"depth map"
text	STRING	required	-	""
clip	CLIP	required	-	-
vae	VAE	required	-	-
per_batch	INT	required	min: 1, max: 4096, step: 1	16
image	IMAGE	optional	-	-
optional_latent	LATENT	optional	-	-

Outputs

Index	Name	Type	Is List	Connection Reference
0	IMAGE	IMAGE	No	["{node_id}", 0]
1	LATENT	LATENT	No	["{node_id}", 1]

How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this Intrinsic_lora_sampling node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

• IMAGE (IMAGE): ["5", 0]
• LATENT (LATENT): ["5", 1]

Package: comfyui-kjnodes