Generate and Edit Images with GPT Image 1.5
OpenAI's latest image generation model with superior instruction following and prompt adherence. GPT Image 1.5 supports text-to-image generation and image editing when input images are provided, with transparent background support and three quality levels priced per image.
What makes GPT Image 1.5 different
Instruction following you can rely on
GPT Image 1.5 is OpenAI's strongest image model for doing what the prompt actually says. Multi-part instructions, specific object placement, in-image text, and stylistic constraints survive generation instead of being averaged away — which matters most when you iterate on a board and need each change to land exactly where you asked.
Three quality levels, priced per image
Pick the quality that matches the job: low quality costs $0.009 per 1024x1024 image and is ideal for drafts and layout explorations, medium is $0.034 for everyday work, and high is $0.133 when the image is the final deliverable. On a Scenetra board you can rough out a concept at low quality and re-run the same node at high quality once the prompt is right.
Editing with input images
Connect one or more input images and GPT Image 1.5 switches from generating to editing: restyle a photo, change an object, combine elements from several sources, or apply a described transformation. The same prompt-adherence strength applies to edits — the model changes what you ask for and leaves the rest alone.
Transparent backgrounds for real assets
The background parameter can force transparent output, so you get PNG assets — logos, stickers, product cutouts, UI elements — that drop straight into designs without a manual background-removal step. Set it to opaque or auto when you want a full scene instead.
Playground
A serene Japanese garden at sunset with cherry blossoms falling, soft golden light filtering through the trees, photorealistic
Drop images or click to upload
Try GPT Image 1.5 in Scenetra
Open PlaygroundParameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Text describing the image you want to generate or edit. | — |
| Image Size | select | Resolution of the output image.auto · 1024x1024 · 1536x1024 · 1024x1536 | 1024x1024 |
| Quality | select | Output quality level — higher quality takes longer.low · medium · high | high |
| Background | select | Background handling for the generated image.auto · transparent · opaque | auto |
| Input Images | image upload | Optional input images for editing. When provided, the model edits rather than generates. | — |
Pricing
From $0.009 per image
Pay per generation — only pay for what you use.
Low quality (1024x1024)
$0.009
per image
Medium quality (1024x1024)
$0.034
per image
High quality (1024x1024)
$0.133
per image
What a video costs
| Duration | 1024x1024 | 1536x1024 | 1024x1536 |
|---|---|---|---|
| Low quality | $0.009 | $0.013 | $0.013 |
| Medium quality | $0.034 | $0.050 | $0.051 |
| High quality | $0.133 | $0.199 | $0.200 |
Use cases
Design & branding
- Logo and icon concepts
- Transparent PNG assets
- In-image text and signage
- Style-consistent asset sets
Marketing & ads
- Ad creative variations
- Product scene mockups
- Campaign key visuals
- Localized text variants
E-commerce
- Product cutouts on transparent backgrounds
- Lifestyle composites from product photos
- Listing image cleanup
- Seasonal variants of existing shots
Content & social
- Blog and article illustrations
- Thumbnail concepts
- Meme and sticker assets
- Photo edits from a text prompt
Related models
Nano Banana Pro
The professional tier of Google's Gemini-powered image generation. Nano Banana Pro delivers higher quality outputs with support for up to 4K resolution, flexible aspect ratios, multiple output formats, and image editing with reference images.
View model →Flux 2 Pro
Black Forest Labs' professional-grade image model delivering high-quality outputs with precise control. Flux 2 Pro supports text-to-image generation and image editing with flexible sizing, safety controls, and simple flat per-image pricing.
View model →Seedream 4.5
ByteDance's upgraded image generation model with improved quality, text rendering, and image editing capabilities. Seedream 4.5 excels at detailed compositions and accurate text in images, making it ideal for marketing and creative content.
View model →Grok Image
xAI's new entrant in AI image generation. Grok Image creates and edits images from text prompts with flexible aspect ratios. A fresh competitor bringing xAI's reasoning capabilities to visual content creation.
View model →Frequently asked questions
What is GPT Image 1.5?+
GPT Image 1.5 is OpenAI's latest image generation and editing model. It generates images from text prompts, edits existing images when you provide input images, and supports transparent backgrounds and three quality levels. On Scenetra it runs as a node in the visual workflow editor — no OpenAI API key or ChatGPT subscription needed.
How much does GPT Image 1.5 cost?+
On Scenetra, GPT Image 1.5 is billed per image by quality and size: low quality starts at $0.009 per 1024x1024 image, medium is $0.034, and high quality is $0.133 (larger 1536x1024 and 1024x1536 sizes cost roughly 1.5x). Edits with input images add a small charge for processing the input image. You only pay for what you generate.
Is GPT Image 1.5 free?+
It's a paid model, but you can try it without paying: new Scenetra accounts start with free welcome credits and a 7-day trial, and at $0.009 per low-quality image those credits go a long way. After that it's pay-per-generation from your credit balance — no subscription gate, nothing to cancel.
Do I need an OpenAI API key to use GPT Image 1.5?+
Not on Scenetra. Sign up, drop a GPT Image 1.5 node onto your board, write a prompt, and generate — Scenetra handles the model access. It's web-based, so it works anywhere without installing anything.
Can GPT Image 1.5 edit existing images?+
Yes. Provide one or more input images and the model switches to editing mode: it can restyle, modify, or combine your images according to the prompt. On a Scenetra board you can wire the output of any other image node straight into GPT Image 1.5 as an editing input.
Is GPT Image 1.5 better than Nano Banana Pro?+
They have different strengths: GPT Image 1.5 is known for instruction following, editing precision, and transparent-background output; Nano Banana Pro (by Google) offers up to 4K resolution and very fast generation. On Scenetra both are on the same board, so you can run the same prompt through each side by side and pick per project instead of committing to one.
Can GPT Image 1.5 generate transparent backgrounds?+
Yes — set the background parameter to 'transparent' and you get PNG output with a real alpha channel, ready to use as a design asset. You can also force 'opaque' or leave it on 'auto' to let the model decide from the prompt.
What image sizes does GPT Image 1.5 support?+
Square 1024x1024, landscape 1536x1024, portrait 1024x1536, or 'auto', which lets the model pick the best fit for your prompt. Each size is available at low, medium, and high quality.
Start creating with GPT Image 1.5
Use GPT Image 1.5 alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started Free