ComfyUI Node
Krea 2 Moodboard + Identity Fusion
Moodboard style + identity edit fused in a single encode (Neo-parity). Both image inputs are optional: ID only = plain identity edit, moodboard only = plain vibe transfer, both = fusion. Positive only; negative = Krea 2 Identity Edit with empty prompt + same image.
Krea 2 Moodboard + Identity Fusion
- clip
- edit_source
- moodboard_images
- vae
- edit_source2
- sources
- target_latent
- CONDITIONING
◄instruction►
◄strength0.50►
◄extract▾►
◄reference_processing▾►
◄style_directivetrue►
◄indirecttrue►
◄budget_px384►
◄grounding_px768►
◄ref_boost1.00►
◄ref_boost_a1.00►
◄fit_modefit►
Categoryconditioning/krea2
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| instruction | STRING | the edit instruction, e.g. 'create a photo of this person at a night market' | |
| strength | FLOAT | 0.500–1 | — |
| extract | COMBO | 2 options: style / vibe, subject / concept | |
| reference_processing | COMBO | 3 options: full image, quadrant crops (2x2), fine tiles (4x4) | |
| style_directive | BOOLEAN | true | — |
| indirect | BOOLEAN | true | delete moodboard rows after encoding; style survives via in-encoder attention. Safest when style refs contain people. |
| budget_px | INT | 384128–1536 | — |
| grounding_px | INT | 7680–2048 | longest-side cap for the edit source fed to the encoder |
| edit_sourceopt | IMAGE | identity source image. Not connected = pure moodboard mode. | |
| moodboard_imagesopt | IMAGE | style references (batch for several). Not connected = pure identity-edit mode. | |
| vaeopt | VAE | connect to attach the in-context identity latents (required for actual editing) | |
| edit_source2opt | IMAGE | 2nd reference for two-ref LoRAs (scene first, subject second) | |
| sourcesopt | KREA2_SOURCES | chained sources (Krea2 Edit Source Chain) — appended after edit_source/edit_source2 as frames 3..N. 3+ refs is beyond the LoRA's training; identities may blend. | |
| ref_boostopt | FLOAT | 1.000–10 | reference-fidelity dial: multiplies target->reference attention for the LAST identity ref (the subject). 1.0 = off; >1 pulls harder toward the reference (the v1.2 edit-LoRA author suggests 2-6). Positive only — the moodboard span is unaffected. |
| ref_boost_aopt | FLOAT | 1.000–10 | same dial for the earlier identity refs (the scene in two-ref workflows). No effect single-ref. 1.0 = off |
| target_latentopt | LATENT | connect your (empty) sampling latent to enable the v1.2 'fit' geometry: identity 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 the same latent to the negative edit node too. | |
| fit_modeopt | COMBO | fit | how identity refs fit a mismatched output AR (needs target_latent + vae): fit = resample to the target grid at a centered offset (v1.2-trained geometry); crop (legacy) = center-crop to the target AR then resize (v1/v1.1 geometry, for older weights). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| CONDITIONING | CONDITIONING | — |