ComfyUI Node
Krea 2 Encode 🆎
Encodes a Krea 2 prompt pair and attaches reference latents in one node. Wire a VAE and a reference image and the reference is encoded and appended to the positive conditioning; leave them unwired and this is a plain two-prompt encoder. The negative comes out of the same node so a turbo graph at CFG 1.0 still has something to plug in without a second text encode sitting there doing nothing.
Krea 2 Encode 🆎
- clip
- vae
- reference
- extra_image
- positive
- negative
◄prompt►
◄negative_prompt►
◄vlm_referencefalse►
Category🆎 AusBoss/Krea2
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| clip | CLIP | The Krea 2 text encoder. | |
| prompt | STRING | Describe the whole finished canvas, not just the new area — the model is generating all of it and matching the reference where it must. | |
| negative_promptopt | STRING | Ignored at CFG 1.0, which is where turbo runs — an empty negative is the normal case there. | |
| vaeopt | VAE | Needed to turn the reference images into latents. Without it the references are skipped. | |
| referenceopt | IMAGE | The `reference` output of Load Image + Pad 🆎 — the unpadded source. Any image works; it is fitted to a multiple of 16 first. | |
| extra_imageopt | IMAGE | A second reference, e.g. a style or character plate. | |
| vlm_referenceopt | BOOLEAN | false | Also show the references to the vision tower, so the text encoder describes them. Off for outpaint — the latents already carry the picture, and the description tends to pull the result toward a paraphrase of the source. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| positive | CONDITIONING | Prompt conditioning with the reference latents attached. |
| negative | CONDITIONING | Negative prompt conditioning. |