AI image model · by OpenAI
GPT Image generator and editor
GPT Image is OpenAI's image generation model family. MotionLab runs the GPT Image versions enabled below for text-to-image and reference-image editing, and any result can go straight into image-to-video.
GPT Image variants available now
These are the GPT Image variants currently enabled on MotionLab and the settings each one accepts. The table is generated from the live model catalog, so it changes when a variant is added, updated or paused.
| Variant | Modes | Resolution | Aspect ratios | Reference images |
|---|---|---|---|---|
| GPT Image 2.5 Sunburst | Text to image · Image editing | 1k · 2k · 4k | auto · 1:1 · 3:2 · 2:3 · 4:3 · 3:4 · 16:9 · 9:16 · 21:9 · 27:16 · 16:27 · 9:8 · 8:9 | Up to 16 |
| GPT Image 2.5 Flare | Text to image · Image editing | 1k · 2k · 4k | auto · 1:1 · 3:2 · 2:3 · 4:3 · 3:4 · 16:9 · 9:16 · 21:9 · 27:16 · 16:27 · 9:8 · 8:9 | Up to 16 |
| GPT Image 2 | Text to image · Image editing | — | 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 5:4 · 4:5 · 2.35:1 · auto | Up to 4 |
What to use GPT Image for
- Images that need legible text, labels or layout.
- Editing an existing image with instructions while keeping the rest intact.
- Product shots and mockups to animate later with a video model.
- Storyboard frames and style frames for a video project.
How to use GPT Image on MotionLab
- Sign in and open the image creation page.
- Choose a GPT Image variant in the model picker. Only the variants listed above are shown.
- Write your prompt, add reference images if you are editing, and pick the size and aspect ratio.
- Check the credit cost shown for your settings, then generate. Failed jobs are refunded automatically.
- Download the image, or send it to the video page as a start frame.
GPT Image prompt tips
- Put exact on-image text in quotes and say where it goes.
- When editing, describe only the change you want and what must stay the same.
- Specify the aspect ratio for the final destination before generating.
- Generate the start frame here, then animate it on the video page.
More technique in the MotionLab prompt guide.
Compare GPT Image with other models
GPT Image questions
Can I edit my own images with GPT Image?
Yes, when the edit mode is enabled: add one or more reference images and describe the change. The specs table shows how many references are accepted right now.
How much does GPT Image cost on MotionLab?
GPT Image generations spend MotionLab credits from the same wallet used by every model on the site. The credit cost for your exact settings is shown before you generate, and a job that fails is refunded automatically. Credit packs are listed on the pricing page.
Do I need a separate OpenAI account or API key?
No. MotionLab runs OpenAI for you: sign in, pick the model in the create page and generate. Your results are saved to your MotionLab library next to work from every other model.
Can I turn a GPT Image result into a video?
Yes. Open the image in your library and send it to the video page as a start frame for any image-to-video model.