Nodes/Krea 2 Reference/Krea 2 Reference Encode
ComfyUI Node

Krea 2 Reference Encode

Encodes a prompt plus up to 4 reference images for Krea 2. References enter as Qwen3-VL vision tokens, enabling character/style/pose transfer ('Redraw the character from image1 in the pose of image2').

By KonokoAz·Created about a month ago·Updated about a month ago· 20
Krea 2 Reference Encode
  • clip
  • image1
  • image1_mask
  • image2
  • image2_mask
  • image3
  • image3_mask
  • image4
  • image4_mask
  • bg_removal
  • CONDITIONING
prompt
image1_detailhigh
image2_detailhigh
image3_detailhigh
image4_detailhigh
layout_split0.00
Categoryconditioning/krea2

Inputs (16)

NameTypeDefaultDescription
clipCLIP
promptSTRINGRoles come from the prompt: character1..4 = identity reference, style1..4 = style-only (patches shuffled). Both expand to the clauses the LoRA trains on. Plain image1..4 / Picture 1..4 also work, e.g. 'Redraw the character from image1 in the pose of image2'.
image1optIMAGE
image1_detailoptCOMBOhighLongest side this reference is scaled to before the vision encoder. Higher = more vision tokens = stronger, more literal reference. Use high for the character/subject and low/normal for pose or style hints to avoid side-by-side collages.
image1_maskoptMASKOptional subject mask (e.g. from RemoveBackground). The reference is cropped to the mask's bounding box and the background is whited out before the vision encoder, so messy references (scenes, watermarks, other characters) only contribute the subject.
image2optIMAGE
image2_detailoptCOMBOhighLongest side this reference is scaled to before the vision encoder. Higher = more vision tokens = stronger, more literal reference. Use high for the character/subject and low/normal for pose or style hints to avoid side-by-side collages.
image2_maskoptMASKOptional subject mask (e.g. from RemoveBackground). The reference is cropped to the mask's bounding box and the background is whited out before the vision encoder, so messy references (scenes, watermarks, other characters) only contribute the subject.
image3optIMAGE
image3_detailoptCOMBOhighLongest side this reference is scaled to before the vision encoder. Higher = more vision tokens = stronger, more literal reference. Use high for the character/subject and low/normal for pose or style hints to avoid side-by-side collages.
image3_maskoptMASKOptional subject mask (e.g. from RemoveBackground). The reference is cropped to the mask's bounding box and the background is whited out before the vision encoder, so messy references (scenes, watermarks, other characters) only contribute the subject.
image4optIMAGE
image4_detailoptCOMBOhighLongest side this reference is scaled to before the vision encoder. Higher = more vision tokens = stronger, more literal reference. Use high for the character/subject and low/normal for pose or style hints to avoid side-by-side collages.
image4_maskoptMASKOptional subject mask (e.g. from RemoveBackground). The reference is cropped to the mask's bounding box and the background is whited out before the vision encoder, so messy references (scenes, watermarks, other characters) only contribute the subject.
bg_removaloptBACKGROUND_REMOVALOptional: connect Load Background Removal Model (birefnet) and every content-role reference is auto-cleaned — cropped to its subject with the background whited out. Per-image masks override it; style-role images are left untouched (their background often carries the style).
layout_splitoptFLOAT0.000–0.9Fraction of the denoise steps that see TEXT-ONLY conditioning before the references kick in. The first steps fix the layout, so 0.25 strongly prevents side-by-side collages of the references. 0 disables.

Outputs (1)

NameTypeDescription
CONDITIONINGCONDITIONING