Edit images using plain-English instructions, directly inside ComfyUI.
This workflow combines Krea 2 Turbo with Krea 2 Identity Edit v1.2 in an organized, fully local setup. Load your image, describe the change, and generate. You can also add an optional second image to guide edits using a visual reference.
What can you do?
Change clothing, outfits, and accessories.
Adjust hair and eye colors.
Change lighting, mood, and time of day.
Modify subjects or details using a second reference image.
Guide edits toward preserving the original composition and surrounding scene.
Preservation depends on the prompt, settings, and complexity of the edit—results are not guaranteed to match every detail.
Workflow features
Clearly labeled sections and setup instructions inside the workflow.
Optional second reference image.
Automatic output resolution matching the source image dimensions, or manually selected width and height.
Adjustable reference fidelity.
Optional Realism Engine LoRA.
Local inference without an external image-generation API.
Quick start
Install the required custom nodes and download the models listed in the workflow.
Select your model files in the loader nodes.
Load your main image. Enable the second image input only when using an additional reference.
Choose automatic or manual output resolution.
Write your editing instruction in English and queue the workflow.
Be specific about both the change and what should stay the same. For example:
“Change the jacket to black leather. Preserve the subject’s face, pose, hairstyle, background, and lighting.”
Start with 10 sampling steps and CFG 1, then adjust reference fidelity as needed.
Requirements and optional LoRA
Model weights are downloaded separately. Follow the included notes for Krea 2 Turbo, the text encoder, VAE, Identity Edit LoRA, and required custom nodes.
Realism Engine is optional. Choose the Krea 2 variant and select it in the Power LoRA Loader. If you do not want to download it, bypass that loader with Ctrl+B. Keep the Identity Edit loader enabled.
Hardware
Tested locally, 10 to 20 seconds per image on an RTX 5090, 64 GB system RAM (depends on the image resolution). This is the tested configuration, not a minimum requirement but I would recommend at least 10-12GB VRAM for a smooth Krea2 Turbo sampling, use more aggressive quantizations if needed (8GB VRAM). Memory use and generation time depend on resolution and model configuration.
Credits
Built using Krea 2 Turbo, Krea 2 Identity Edit, and the comfyui-krea2edit custom nodes. Credit goes to their respective creators and the creators of the optional dependencies.
Feedback and example results are welcome! When reporting an issue, please include your settings and the relevant error message.