ImageOpenAI
GPT Image 2
Photorealistic images & precise edits with top-tier instruction following.
GPT Image 2 is OpenAI's image model — known for accurate prompt following, clean in-image text rendering, and reliable edits. Generate from scratch or upload an image and describe exactly what to change, add, remove, or restyle.
Generated with GPT Image 2
Capabilities
- Text → Image
- Image edit (add / remove / restyle)
- Accurate in-image text
- Strong instruction following
At a glance
- Output
- Up to 4K (upscaled)
- Inputs
- Text · Image
- Strength
- Prompt accuracy & text
- Best for
- Product, posters, edits
Sample outputs
Official sample outputs from GPT Image 2.
Use via API
For developersOne endpoint, one key — just switch the model parameter to call any model. No need to integrate OpenAI directly, manage separate billing, or maintain four SDKs.
curl -X POST https://pixmo.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $PIXMO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"inputs": { "prompt": "your prompt here" }
}'
# returns { "taskId": "..." } — then poll:
curl "https://pixmo.ai/api/v1/jobs/queryTask?taskId=TASK_ID" \
-H "Authorization: Bearer $PIXMO_API_KEY"
