ComfyUI Node
Krea 2 Moodboard Encode (packed)
Moodboard conditioning with all references packed into one vision span. Use standalone (with prompt) or as the fuse_with feeder for Krea 2 Identity Edit (empty prompt).
Krea 2 Moodboard Encode (packed)
- clip
- images
- CONDITIONING
◄prompt►
◄strength0.50►
◄extract▾►
◄reference_processing▾►
◄style_directivetrue►
◄indirectfalse►
◄position▾►
◄budget_px384►
Categoryconditioning/krea2
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | — | |
| prompt | STRING | — | |
| strength | FLOAT | 0.500–1 | 1.0 = raw reference detail; lower = purer extract of the selected aspect |
| 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 | false | hide reference tokens from the DiT: style arrives only via prompt re-contextualization; cannot copy pose/subject |
| position | COMBO | 2 options: before prompt, after prompt | |
| budget_px | INT | 384128–1536 | area budget per reference fed to the vision encoder |
| imagesopt | IMAGE | reference images (batch them for multiple); leave unconnected for a plain Krea 2 text encode |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| CONDITIONING | CONDITIONING | — |