Nodes/ComfyUI-Krea2Moodboard/Krea 2 Identity Edit
ComfyUI Node

Krea 2 Identity Edit

A ComfyUI node in conditioning/krea2 with 12 inputs and 1 output.

By RedNodeAI·Created about a month ago·Updated 28 days ago· 9
Krea 2 Identity Edit
  • clip
  • vae
  • image
  • image2
  • fuse_with
  • sources
  • target_latent
  • CONDITIONING
prompt
grounding_px768
ref_boost1.00
ref_boost_a1.00
fit_modefit
Categoryconditioning/krea2

Inputs (12)

NameTypeDefaultDescription
clipCLIP
promptSTRINGEdit instruction. Leave empty on the negative node.
vaeoptVAE
imageoptIMAGE
image2optIMAGE
grounding_pxoptINT7680–4096Cap on the longest side fed to Qwen3-VL (the identity LoRA trained with 384-768px). 0 = never resize.
fuse_withoptCONDITIONINGOptional conditioning to fuse in front of this one (e.g. Krea 2 Moodboard for scene/style vibe). Its token rows are prepended; this node's identity reference latents are kept. Matches the Neo moodboard+edit fusion layout.
sourcesoptKREA2_SOURCESchained sources (Krea2 Edit Source Chain) — appended after image/image2 as frames 3..N. 3+ refs is beyond the LoRA's training; identities may blend.
ref_boostoptFLOAT1.000–10reference-fidelity dial: multiplies target->reference attention. Applies to the LAST ref (the subject in two-ref workflows, the only ref in single-ref). 1.0 = off; >1 pulls harder toward the reference's appearance (the v1.2 edit-LoRA author suggests 2-6); <1 loosens. Set on the POSITIVE node; leave the negative at 1.0.
ref_boost_aoptFLOAT1.000–10same dial for the earlier refs (the scene in two-ref workflows). No effect in single-ref workflows. 1.0 = off
target_latentoptLATENTconnect your (empty) sampling latent to enable the v1.2 'fit' geometry: refs are fitted in PIXEL space to the output resolution before VAE-encoding — fixes blur from resolution mismatch and removes the match-the-aspect-ratio requirement. With CFG > 1, connect it to the negative edit node too so both passes share one geometry.
fit_modeoptCOMBOfithow refs fit a mismatched output AR (needs target_latent + vae): fit = resample to the target grid at a centered offset, matching how the v1.2 edit LoRA was trained; crop (legacy) = center-crop to the target AR then resize (v1/v1.1 geometry, for older weights).

Outputs (1)

NameTypeDescription
CONDITIONINGCONDITIONING