Imageopenaigpt-image-2-text-to-image

GPT Image 2

OpenAI's text-to-image with extremely detailed typography and strong instruction-following.

Open in Image Lab Browse all models~37 cr 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.

About this variant

Newer OpenAI image model — supports 20k-char prompts.

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_urls
array
Optional. Add image(s) to edit them instead of generating from text.
image_size
string
No description.
autosquare_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
default: auto
quality
string
No description.
lowmediumhigh
default: high
num_images
int
No description.
default: 1
range: 1 … 4
output_format
string
No description.
jpegpngwebp
default: png