Image editgptgpt4o-edit

Gpt4o Edit

Edit a specific part of an image using natural language. Ideal for object removal, replacement, or content-aware filling.

Open in Image Lab Browse all models~5 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

image_url
string
URL of the input image to erase from.
mask_image_url
string
The URL of the binary mask image that represents the area that will be cleaned.
aspect_ratio
string
Aspect ratio of the output image.
1:12:33:2
default: 1:1
num_images
int
Number of images generated in single request. Each number will charge separately
124
default: 1

You'll need

A text prompt
Source image
Mask imageoptional

Try now

More from gpt

Gpt Image 2 Text To Image

gpt-image-2-text-to-image