What is GPT Image 1.5?

GPT Image 1.5, released December 2025, is OpenAI's most capable image model. Built into the GPT-5 architecture, it generates images 4× faster than GPT Image 1, with 20% lower cost. It excels at preserving original image details during edits — no more complete re-renders. Text rendering is significantly improved, handling dense and small characters accurately.

What's New in 1.5

4× faster generation speed
20% cheaper than GPT Image 1
Preserves original image elements during edits (no re-renders)
Significantly better text rendering — dense, small, accurate
Maintains visual consistency across multiple generations
Handles complex scenes with multiple objects reliably
Built directly into GPT-5 architecture

API Pricing

GPT Image 1.5 is 20% cheaper than GPT Image 1. Text input: $5/1M tokens. Image input: $8/1M tokens. Image output: $32/1M tokens. Typical cost: ~$0.01–$0.05 per image.

Production-grade use cases

Hero shots & key visuals

Photoreal lead images for landing pages, decks, and editorials — precise composition, consistent lighting, magazine-quality output.

Brand-consistent visuals

Generate sets of images that hold the same palette, lighting, and styling across multiple shots — ideal for content systems.

Multi-shot campaigns

Spin up coordinated ad creatives in one session: same model, same brand language, different formats and aspect ratios.

Detailed product editing

Fix labels, swap colorways, or extend backgrounds without re-rendering the rest of the image — original details stay intact.

Localized text graphics

Render dense and small text with high accuracy — useful for translations, multi-region campaigns, and regulated copy.

High-fidelity variations

Generate variant after variant with predictable changes — perfect for A/B tests, mood exploration, and design reviews.

How to use GPT Image 1.5

1
Select GPT Image 1.5
Open the playground above and pick gpt-image-1.5. Free credits land in your account at sign up — no payment required to start.
2
Describe the result you want
Use plain English or Chinese. Mention style, lighting, composition, and any on-image text. Reference real photography terms if you know them.
3
Generate or edit
For new images, just generate. For edits, upload a reference and mask the region to change — 1.5 will preserve everything outside the mask.
4
Iterate fast
Tweak the prompt, change the size, or seed a new variation. 1.5 is 4× faster than 1.0, so iteration is cheap and immediate.

GPT Image 1.5 vs GPT Image 1

	GPT Image 1	GPT Image 1.5
Speed	Standard	4× faster
Edit fidelity	May re-render entire image	Preserves details precisely
Text rendering	Good	Best in class
Consistency	Variable across generations	Consistent style and composition
Complex scenes	Can struggle	Handles reliably
Price (output)	$40/1M tokens	$32/1M tokens

Frequently Asked Questions

Yes. New users on imagesv2.ai get free credits on sign up — enough to test generation, editing, and several quality tiers before any top-up.

Same model family, but faster (4×), cheaper (20%), and better at preserving details when you edit. Text rendering is also significantly improved. For most production work, 1.5 is the better choice.

Yes. Upload a reference, mask the region you want to change, and describe the edit. 1.5 preserves everything outside the mask precisely — no full re-renders.

Square 1024×1024, landscape 1536×1024, and portrait 1024×1536. All sizes support PNG, JPEG, and WebP output, including transparent backgrounds.

Yes — OpenAI exposes it as gpt-image-1.5 in the Images API. On imagesv2.ai you can use it without managing API keys, billed in credits.

GPT Image 2 is even faster (sub-3s) with native reasoning and 99%+ text accuracy. If you need cutting-edge quality and have credits to spare, use 2. For balanced cost/quality, 1.5 is excellent.

Try GPT Image 1.5 now

Sign in above to claim your free credits and start generating with OpenAI's most capable image model. Credits also work across GPT Image 1 and GPT Image 2 — pick whichever fits the shot.

This generation costs: 10 credits

History

Generated images will appear here.

How to Use the GPT Image 2 Playground

GPT Image 2 Parameter Guide

Quality Comparison (gpt-image-2)

Quality	Speed	Image Detail	Credits/Image	Best For
Low	Fastest (3-8s)	Good composition, less detail	10	Quick iterations, bulk generation, social media
Medium	Moderate (10-20s)	Rich details, good textures	40	Marketing images, presentations
High	Slower (20-40s)	Highest fidelity, finest details	110	Print, posters, premium assets
Auto	Model decides	Auto-selected by model	40	When unsure

Model Comparison

Model	Highlights	Low/Image	High/Image
gpt-image-2	Latest, best results	10	110

Cost-Saving Tips

Start with Low quality to iterate on prompts, then switch to Medium or High for the final version.
Credits scale with image count: per-image cost × number of images.
New users get a 3-credit first-trial bonus on the standard tier (one-time).

GPT Image 2 Text-to-Image Generation

Enter a text prompt describing the image you want. Adjust parameters like size (Square, Landscape, Portrait), quality (Low/Medium/High), output format (PNG/JPEG/WebP), and background (Opaque or Transparent). Click "Generate" and GPT Image 2 will create a brand-new image from your description.

Tips for Better GPT Image 2 Results

Be specific and detailed in your prompt — describe lighting, composition, style, and mood.
Use "Transparent" background to get cutout images for product photos, stickers, and design assets.
Low quality is fastest and cheapest; High quality gives the best results but costs more.
Generate multiple GPT Image 2 images (up to 10) to compare different interpretations of your prompt.

GPT Image 2 Image Editing (Inpainting)

Upload a source image, write a prompt describing the changes you want, and GPT Image 2 will modify the image accordingly. Without a mask, GPT Image 2 decides which areas to change. With a mask, you can precisely control which regions are modified.

How the Mask Editor Works

Upload your source image in Edit mode.
Click "Create Mask" to open the mask editor.
Draw on the image with the brush — the red areas you paint will become the editable regions.
Adjust the brush size slider for fine or coarse control.
Click "Save Mask" to generate the mask file. You'll see a preview (black = keep, transparent = edit).
Write a prompt describing what should appear in the masked areas.
Click "Edit Image" to submit.

GPT Image 2 Image-to-Image (Style Transfer)

You can use Edit mode for GPT Image 2 image-to-image generation without a mask. Simply upload a reference image and describe the transformation you want in the prompt — for example, "Convert this photo to a watercolor painting" or "Reimagine this scene in a cyberpunk style". GPT Image 2 will use your image as a reference to generate a new version.

Example GPT Image 2 Prompts for Image-to-Image

"Convert this photo to Studio Ghibli anime style"
"Reimagine this scene as a 3D rendered illustration"
"Transform this into a vintage oil painting"
"Make this look like a professional product photo with white background"

Edit Image

Modify an existing image with a text prompt.

History

Generated images will appear here.

How to Use the GPT Image 2 Playground

GPT Image 2 Parameter Guide

Quality Comparison (gpt-image-2)

Quality	Speed	Image Detail	Credits/Image	Best For
Low	Fastest (3-8s)	Good composition, less detail	10	Quick iterations, bulk generation, social media
Medium	Moderate (10-20s)	Rich details, good textures	40	Marketing images, presentations
High	Slower (20-40s)	Highest fidelity, finest details	110	Print, posters, premium assets
Auto	Model decides	Auto-selected by model	40	When unsure

Model Comparison

Model	Highlights	Low/Image	High/Image
gpt-image-2	Latest, best results	10	110

Cost-Saving Tips

Start with Low quality to iterate on prompts, then switch to Medium or High for the final version.
Credits scale with image count: per-image cost × number of images.
New users get a 3-credit first-trial bonus on the standard tier (one-time).

GPT Image 2 Text-to-Image Generation

Tips for Better GPT Image 2 Results

Be specific and detailed in your prompt — describe lighting, composition, style, and mood.
Use "Transparent" background to get cutout images for product photos, stickers, and design assets.
Low quality is fastest and cheapest; High quality gives the best results but costs more.
Generate multiple GPT Image 2 images (up to 10) to compare different interpretations of your prompt.

GPT Image 2 Image Editing (Inpainting)

How the Mask Editor Works

Upload your source image in Edit mode.
Click "Create Mask" to open the mask editor.
Draw on the image with the brush — the red areas you paint will become the editable regions.
Adjust the brush size slider for fine or coarse control.
Click "Save Mask" to generate the mask file. You'll see a preview (black = keep, transparent = edit).
Write a prompt describing what should appear in the masked areas.
Click "Edit Image" to submit.

GPT Image 2 Image-to-Image (Style Transfer)

Example GPT Image 2 Prompts for Image-to-Image

"Convert this photo to Studio Ghibli anime style"
"Reimagine this scene as a 3D rendered illustration"
"Transform this into a vintage oil painting"
"Make this look like a professional product photo with white background"

GPT Image 1.5 — AI Image Generator Online

Production-grade use cases

Select GPT Image 1.5

Describe the result you want

Generate or edit

Iterate fast

Looking for a different tool?

How to Use the GPT Image 2 Playground

How to Use the GPT Image 2 Playground

GPT Image 1.5 — AI Image Generator Online

Production-grade use cases

Select GPT Image 1.5

Describe the result you want

Generate or edit

Iterate fast

Is GPT Image 1.5 free to try?

How does 1.5 compare to GPT Image 1?

Can I edit existing images?

What sizes and aspect ratios are supported?

Is GPT Image 1.5 available via API?

Should I use 1.5 or GPT Image 2?

Looking for a different tool?

How to Use the GPT Image 2 Playground

How to Use the GPT Image 2 Playground