AI Image Generator — Create from Text or References
Start an image from a written description or add reference photos. GPT Image 2.5 Flare is selected, and other available models are in the selector.
Create a video from a text prompt, without reference uploads.
Enter at least 3 characters to continue.
What you can create with AI Image Generator
Choose output size and framing for where the image will be used. Reference limits differ by model; the tool updates its upload slots and resolution options when you switch.
When to use this tool
Use AI Image Generator to develop a poster, campaign still or page illustration from a brief, choosing the model and output shape for the final placement.
The default GPT Image 2.5 Flare setup supports up to 16 references, but its 27:16, 16:27, 9:8 and 8:9 ratios are 1K only. For an edit centred on an existing photograph, AI Image Editor starts with a required source-image workflow.
A prompt to adapt
A tabletop photo of a handmade ceramic mug, pale linen background, morning side light, centered composition with space above for a headline.
Tool specifications
- Model
- GPT Image 2.5 Flare
- Output resolution
- 1K / 2K / 4K
- Reference images
- Up to 16 images
- Aspect ratios
- 1:1 · 3:2 · 2:3 · 16:9 · 9:16 · 4:3 · 3:4 · 21:9 · 27:16 · 16:27 · 9:8 · 8:9
How to use AI Image Generator
- 01
Prepare your brief
Describe the intended result and add the files required by the selected workflow.
- 02
Choose and review settings
The matching model or Agent is already selected. Review its settings, inputs and credit estimate.
- 03
Generate and review
Sign in to submit the task, follow its progress and review the output or storyboard in your workspace.
Check the quote before generating
The live estimate depends on the model, settings and input materials. Sign in and use generation credits to submit a task; review the quote in the tool before you start.
Image credits follow the selected model and output settings. With the default GPT Image 2.5 Flare model, the quote is per generated image at the selected resolution.
View plans and creditsQuestions about this tool
Can I use reference images as well as text?
Yes, for models that support references. The selected GPT Image 2.5 Flare model accepts up to sixteen. Z-Image uses text only, while Qwen Image Edit requires a source image.
Do I need an account?
You can explore the tool and its settings on this page. Sign in to upload task materials, submit generation requests and save results to your workspace.
How are generation credits calculated?
Credits depend on the selected model, duration, resolution and input materials. Review the current estimate before submitting. Agent projects may include several generation tasks, each with its own credit usage. Image credits follow the selected model and output settings. With the default GPT Image 2.5 Flare model, the quote is per generated image at the selected resolution.
Where can I find and download my results?
Completed results are available in your workspace. Open the task to preview or download its files. For an Agent project, review the storyboard and the assembled video in the project.