GPT Image 1.5 I2I: AI Image Editor Online
Bottom line
OpenAI's GPT Image 1.5 editor: up to 10 images, medium or high quality — both cost the same flat 10 credits. Open the Image Edit tool, select GPT Image 1.5 I2I, upload your image, and the exact credit cost appears before the edit runs.
The case for GPT Image 1.5 I2I is comprehension. Because it comes from OpenAI's GPT multimodal stack, it parses editing instructions the way a language model parses text — long, conditional, multi-step prompts such as "swap the jacket to denim, keep the logo intact, match the lighting from the left" tend to survive as written instead of collapsing into an approximate restyle.
The spec sheet is deliberately narrow: attach up to 10 images per edit, choose medium or high quality, and work in three aspect ratios — square 1:1, portrait 2:3, or landscape 3:2. Prompts run up to 3,000 characters. There's no ultrawide format and no transparent-background option in VdoBloom's implementation; the model spends its effort on executing the requested change faithfully at sensible sizes rather than offering a wide format menu.
It carries VdoBloom's CENSORED-tier STRICT content label, reflecting OpenAI's conservative provider filters, and holds a 4.4 user rating. Every edit — medium or high quality — costs a flat 10 credits, shown before you generate.
What it costs on VdoBloom
10 credits per edit, flat — the quality setting (medium or high) doesn't change the price. Your 10 free signup credits cover exactly one edit; after that you're drawing from a paid balance. The cost is shown before you commit, and a failed generation is refunded automatically.
GPT Image 1.5 vs GPT Image 2
Both come from OpenAI's GPT image stack, but they're priced and specced differently on VdoBloom. GPT Image 1.5 is flat-rate (10 credits) and narrow (1:1/2:3/3:2, up to 10 images, 3,000-character prompts). GPT Image 2 is resolution-tiered (3/5/8 credits at 1K/2K/4K) with 11 aspect ratios including auto, the same 10-image limit for editing, and a much longer 20,000-character prompt budget. At 1K or 2K, GPT Image 2 is cheaper per edit than 1.5's flat rate; only at 4K does it cost more.
Prompting tips for instruction-heavy edits
Because GPT Image 1.5 comprehends prompts more like a language model than a typical diffusion editor, write instructions as explicit, ordered steps rather than a mood description — name exactly what changes, what stays fixed, and any text that must render correctly. Keep it under 3,000 characters and remember the price doesn't change if you bump quality to high, so there's no cost reason to default to medium.
What creators use GPT Image 1.5 I2I for
- Multi-step product edits where instructions must be followed literally — change the color, preserve the label text, adjust the shadows.
- Instruction-driven composites that pull from up to 10 reference photos in one job.
- Edits involving legible text — packaging, signage, UI mockups — where prompt comprehension matters more than raw resolution.
How to use GPT Image 1.5 I2I on VdoBloom
- 1Open the Image Edit tool and select GPT Image 1.5 I2I.
- 2Upload the image(s) to edit and describe the change you want.
- 3Review the credit cost and generate — results appear in your library.
Frequently asked questions
How much does GPT Image 1.5 I2I cost on VdoBloom?
A flat 10 credits per edit. Choosing medium or high quality changes rendering effort, not price — both settings cost the same 10 credits.
Is GPT Image 1.5 free to try?
New accounts get 10 free signup credits, which covers exactly one GPT Image 1.5 edit before you need to add credits.
How many images can I attach to one edit?
Up to 10 per job. The model treats them as joint context for your instruction, useful when a single change needs to reference several sources — a subject from one photo, a texture from another.
Does the medium vs high quality setting change the price?
No. It only affects rendering effort and detail — high produces cleaner output, medium is quicker for drafts — but VdoBloom charges the same flat 10 credits either way.
Will GPT Image 1.5 refuse my prompt?
It can. The model carries VdoBloom's STRICT content label, reflecting OpenAI's conservative provider filters. Requests involving real people, violence, or suggestive content have a higher chance of being declined than on models tagged HOT.
Why does GPT Image 1.5 only offer 1:1, 2:3, and 3:2 aspect ratios?
Those are the frames VdoBloom's integration supports for this model. If you need ultrawide or other formats, generate at 3:2 or 2:3 and crop afterward, or use GPT Image 2, which supports 11 aspect ratios including auto.
Does GPT Image 1.5 support transparent backgrounds?
Not in VdoBloom's implementation — its settings expose only aspect ratio and quality, with no output-format or background control.
How does GPT Image 1.5 compare to GPT Image 2?
GPT Image 2 is the newer, more flexible model: 11 aspect ratios instead of 3, resolution-tiered pricing (3/5/8 credits at 1K/2K/4K, so it's often cheaper than 1.5's flat 10) instead of a single flat rate, and a 20,000-character prompt limit versus 1.5's 3,000. GPT Image 1.5 remains available for existing workflows built around it.
When did GPT Image 1.5 launch on VdoBloom?
2025-12-16.