Prompt-adherence enhancement for Krea2 diffusion models in ComfyUI.
This custom node patches the Krea2 text-fusion path during sampling and applies a controlled internal conditioning adjustment intended to improve how strongly the model follows prompt details.
cd ComfyUI/custom_nodes
git clone https://github.com/capitan01R/ComfyUI-Krea2T-Enhancer.gitRestart ComfyUI after installing or updating.
No extra Python packages are required beyond a working ComfyUI Krea2 setup.
| Node | Output | Purpose |
|---|---|---|
| ComfyUI-Krea2T-Enhancer | MODEL |
Patches the Krea2 model path to improve prompt adherence during sampling. |
Place ComfyUI-Krea2T-Enhancer between your Krea2 diffusion model loader and sampler:
Load Diffusion Model -> ComfyUI-Krea2T-Enhancer -> KSampler
Use your normal Krea2 text encoder, VAE, latent, and sampler setup.
| Parameter | Default | Meaning |
|---|---|---|
enabled |
true |
Turns the patch on or off. |
strength |
1.0 |
Blends the enhancement from neutral 0.0 to full 2.0. |
debug |
false |
Prints concise runtime diagnostics to the ComfyUI console. |
- Designed for Krea2 models using the
12 x 2560Krea2 text-conditioning layout. - The node returns only a patched
MODEL; it does not modify prompt text or require extra conditioning nodes. - If the loaded model does not match the expected Krea2 text-fusion layout, the patch is skipped.