Skip to content

AI Image Edit

Node icon
AI

Edits existing images with text instructions using AI. Restyle, combine references, or turn sketches into art.

AI Image Edit takes one or more input images and applies text-based edits using AI. Pick the model that fits the edit: Nano Banana 2 for restyling and multi-image fusion, GPT Image 2 Edit when the result needs readable text or strict prompt adherence, or the FLUX.2 models when you want classic photoreal output and per-megapixel pricing.

Five models are available: FLUX.2 Turbo (fast, affordable edits), FLUX.2 Pro (professional quality), FLUX.2 Max (highest fidelity), Nano Banana 2 (multi-image fusion and complex creative edits), and GPT Image 2 Edit (designer-grade output and the best in-image text rendering of any model). All five accept up to three reference images on the ref_1, ref_2, and ref_3 pins for multi-image fusion.

FLUX.2 Pro, FLUX.2 Max, and GPT Image 2 Edit each expose an Output Size combo with Auto (match the input dimensions) plus six presets from 1024×768 up to 3840×2160. Picking a smaller preset is the main way to keep the per-megapixel cost down when editing a large input image.

Pins

ImageImage
InputRequired
Ref 1Image
InputOptional
Ref 2Image
InputOptional
Ref 3Image
InputOptional
ImageImage
Output

Prompt

Edit InstructionText

Instruction describing the edit

Model

ModelChoice
Default: 1 Range: FLUX.2 Turbo / FLUX.2 Pro / FLUX.2 Max / Nano Banana 2 / GPT Image 2 Edit

AI model

Generation

SeedInteger
Default: -1 Range: -1–999999

Generation seed; -1 = random (not supported by GPT-2 Edit)

Aspect RatioChoice
Default: 0 Range: Auto / 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16
Model = Nano Banana 2

Output aspect ratio

ResolutionChoice
Default: 1 Range: 0.5K / 1K / 2K / 4K
Model = Nano Banana 2

Output resolution

Web SearchToggle
Default: false
Model = Nano Banana 2

Enable web search augmentation

Output SizeChoice
Default: 0 Range: Auto (use input size) / 1024x768 (4:3) / 1024x1024 (1:1) / 1024x1536 (2:3) / 1920x1080 (16:9) / 2560x1440 (16:9 QHD) / 3840x2160 (16:9 4K)
Model = FLUX.2 Pro or FLUX.2 Max

FLUX Edit output size. Auto matches input

Output SizeChoice
Default: 0 Range: Auto (use input size) / 1024x768 (4:3) / 1024x1024 (1:1) / 1024x1536 (2:3) / 1920x1080 (16:9) / 2560x1440 (16:9 QHD) / 3840x2160 (16:9 4K)
Model = GPT Image 2 Edit

GPT Image 2 Edit output size

QualityChoice
Default: 1 Range: Low / Medium / High
Model = GPT Image 2 Edit

Generation quality

  • Use Nano Banana 2 for the best results on complex restyling and multi-image fusion.
  • Reach for GPT Image 2 Edit when the edit has to preserve or replace readable text (UI mockups, signage, labels) or when a complex multi-clause edit instruction has to be followed exactly.
  • On FLUX.2 Pro / Max and GPT Image 2 Edit, drop Output Size to a smaller preset to cut the per-megapixel cost when editing a 4K source.
  • Wire multiple images as input for reference-driven generation; the AI combines them.
  • Be specific in your edit instruction: “make the background a sunset” is better than “change background.”
  • Use Enable Web Search for reference-based edits that need real-world knowledge (Nano Banana 2 only).