Nodes/ComfyUI-DonutNodes/Donut Krea2 Image Conditioning
ComfyUI Node

Donut Krea2 Image Conditioning

A ComfyUI node in Donut/conditioning with 12 inputs and 1 output.

By DonutsDelivery·Created about a year ago·Updated a day ago· 22
Donut Krea2 Image Conditioning
  • clip
  • image1
  • image2
  • image3
  • vae
  • conditioning
prompt
text_strength1.00
rebalancetrue
strength11.00
strength21.00
strength31.00
multiplier1.00
CategoryDonut/conditioning

Inputs (12)

NameTypeDefaultDescription
clipCLIPKrea2 CLIP model (Qwen3-VL 4B)
promptSTRINGText instruction describing the edit or generation
text_strengthFLOAT1.000–10Text influence: 0=no text baseline, 1=full, >1=overemphasis
rebalanceBOOLEANtrueReboost blended conditioning to match the requested text_strength magnitude. When lowering image strength, text gets proportionally louder so overall CFG stays constant.
image1optIMAGEFirst reference image
strength1optFLOAT1.000–10Image1 influence: 0=text-only, 1=full, >1=overemphasis
image2optIMAGESecond reference image
strength2optFLOAT1.000–10
image3optIMAGEThird reference image
strength3optFLOAT1.000–10
vaeoptVAEOptional VAE. Stores reference_latents on the conditioning for forward-compatibility.
multiplieroptFLOAT1.00-1000–1000Global gain on the conditioning tensor. 1.0 = unchanged.

Outputs (1)

NameTypeDescription
conditioningCONDITIONING