ComfyUI Node: Krea Reason (expand prompt + encode)

Authored by shootthesound

Created

Updated

10 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

ShootTheSound/KreaReason

Inputs

clip CLIP
prompt STRING
mode
  • expand
  • think
max_new_tokens INT
temperature FLOAT
seed INT
image IMAGE
image_remove
  • nothing (keep full description)
  • people (and all they wear/hold)
  • the main subject
  • people + main subject (keep the scene)
  • the background (keep the subject)
  • everything except clothing
  • everything except style
  • everything except colors
  • everything except composition
  • custom
custom_image_instruction STRING
image_megapixels FLOAT
instruction STRING
top_p FLOAT
cond_boost FLOAT

Outputs

CONDITIONING

STRING

Extension: Krea Reason

Reason-then-encode for Krea 2. The encoder's own Qwen3-VL rewrites your prompt into a richer one — or reads a reference image (describe → filter → combine) — before conditioning: a built-in prompt enhancer and language-level image reference, running on the exact model that conditions.

Authored by shootthesound

View Nodes

Looking for a different node?

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more