Image editgpt-1.5gpt-image-1.5-edit

Gpt Image 1.5 Edit

GPT-Image-1.5 Edit applies precise, instruction-based modifications to an existing image while preserving composition, lighting, perspective, and visual coherence. It’s well-suited for object replacement, concept evolution, symbolic edits, and creative transformations that feel natural and intentional rather than destructive.

Open in Image Lab Browse all models~25 credits per run

GPT guideVerified

OpenAI's image lines. GPT Image 1.5 (text-to-image) and GPT Image 2 (text-to-image + image-to-image with up to 16 references) are the flagships. GPT-4o Image is the multimodal-chat variant.

Strengths

Best instruction-following + scene composition in our image catalog.
GPT Image 2 accepts up to 16 reference images for style transfer / editing.
Reliable for typography (better than Midjourney, behind Ideogram).
Multimodal understanding — interprets reference images at semantic level, not just visual.

Weaknesses

Premium pricing.
Filters reject more prompts than competitors.
Stylization is OK but not its strength.

Best for

Complex scene composition with explicit positioning
Brand-consistent work via reference packs (16 images)
Diagrams, infographics, slides with text

Prompting tips

Be explicit about subjects, positions, what's where.
Long prompts work — GPT 2 supports up to 20,000 characters.
Reference packs: include shots of the SAME subject from multiple angles for best consistency.

Parameters

mask_image_url
string
The URL of the mask image to use for the generation. This indicates what part of the image to edit.
quality
string
Quality for the generated image
lowmediumhigh
default: high
image_size
string
Aspect ratio for the generated image
auto1024x10241536x10241024x1536
default: auto
output_format
string
Output format for the images
jpegpngwebp
default: png
num_images
int
Number of images to generate
default: 1
range: 1 … 4
image_urls
array
The URLs of the images to use as a reference for the generation.
background
string
Background for the generated image
autotransparentopaque
default: auto
input_fidelity
string
Input fidelity for the generated image
lowhigh
default: high

You'll need

A text prompt
Source images
Mask imageoptional

Try now

More from gpt-1.5

Gpt Image 1.5

gpt-image-1.5