GPT Image 2.5 Flare Edit

OpenAI GPT Image 2.5 Flare Edit, fast multi-image edit and composite. Wire up to 10 images (Image 1..10) plus an optional mask; the prompt describes the change. Good at placing a real product into a generated scene with the label intact. Same price as Sunburst Edit: draft here, ship on Sunburst Edit. Prefer one edit from the clean source over edits of edits, which add noise and drift, and repeat the preserve list in every edit prompt.

Try GPT Image 2.5 Flare Edit in the playground

Last updated View as Markdown

GPT Image 2.5 Flare Edit

Node type: edit:openai_gpt_image_2_5_flare_edit
Category: edit

Description

GPT Image 2.5 Flare Edit is OpenAI's fast tier for editing and compositing images: wire up to 10 images into Image 1 onward, add an optional Mask, write the change in Prompt, and run the node. It is good at placing a real product into a generated scene with the label intact. Repeat the list of things to keep in every edit prompt. Set Background to auto, transparent or opaque, and the output to jpeg, png or webp. It costs about 20 credits per image, the same as the GPT Image 2.5 Sunburst Edit node, so draft here and ship the final frame there.

Pricing

  • Cost: ~20 credits per images

Variant family

  • Family: gpt-image-2.5-flare
  • Is primary: no
  • All variants: generate:openai_gpt_image_2_5_flare_text_to_image, edit:openai_gpt_image_2_5_flare_edit

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required) · multiline
image1 Image 1 IMAGE (required)
mask_url Mask IMAGE

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
quality Quality TEXT · options: low, medium, high, xhigh, max
image_size Image Size IMAGE_SIZE · options: custom, square_hd, portrait_4_3, landscape_4_3, auto, +1 — Match input keeps the first image’s resolution, rounded to 16px. Sizes are scaled to fit 0.66 to 8.29 megapixels and a 3840px edge. Inputs wider or taller than 3:1 need cropping or a custom output size. Custom sizes above 2560x1440 are experimental and can come out over-sharpened.
num_images Number of Images NUMBER · 1…4
output_format Output Format TEXT · options: jpeg, png, webp
background Background TEXT · options: auto, transparent, opaque
output_compression Output Compression NUMBER · 0…100
sync_mode Sync Mode BOOLEAN

Outputs

ID Label Type
images Generated Images IMAGE

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.