A ComfyUI custom node that uses the Gemini API to rewrite a raw prompt into one optimised for a specific image generation model and workflow.

Monks-Prompt-Enhancer-ComfyUI-Node

Uses the Gemini API to rewrite a raw prompt into one optimised for a specific image generation model and workflow.

Select the Target Image Generation Model to apply the right prompting strategy:
  • Gemini Nano Banana — narrative prose structured around subject, setting, lighting, and atmosphere.
  • FLUX.2 Klein — flowing descriptive prose (no keyword lists); concise action-oriented edits for img2img; simple explicit references for multi-image composition.

Select the Purpose to match your workflow:
  • Text to Image — expands a raw idea into a detailed, model-ready prompt.
  • Image Editing — strips out base-image descriptions and returns only the transformational action.
  • Multi Image Fusion — produces a minimal explicit reference prompt (e.g. 'change image 1 to match the style of image 2').

Connect a Reference Image (optional) to include it in the Gemini call as visual context.

ComfyUI Node: Monks Image Generation Prompt Enhancer

Category

Inputs

Outputs

Extension: Monks-Prompt-Enhancer-ComfyUI-Node

Run ComfyUI workflows without the setup