# GPT Image 2.5 and GPT Image 2

> Run OpenAI's GPT Image 2.5 and GPT Image 2 in Faceless: photoreal people, sets and lighting from a long brief, up to 4K, with up to 16 reference pictures. Prices in credits, a real sample, and a prompt box.

Canonical: https://faceless.so/models/gpt-image
Last updated: 2026-11-12

AI model

OpenAI's image model for photoreal people, sets and lighting from a long brief. Run it in Faceless from a prompt or your own pictures.

Updated November 12, 2026 · By Faceless

## GPT Image is OpenAI's image model, and Faceless runs GPT Image 2.5 and GPT Image 2

**GPT Image 2.5 turns a written brief into a photoreal picture at 1K, 2K or 4K in 8 shapes, and can work from up to 16 of your own pictures.** A picture is 1 credit at 1K and 2 credits at 2K. Type a prompt below and it opens in the Faceless Text to Image studio with the version you pick.

![A photoreal old fisherman mending a green net on a wooden dock at dawn, mist on the water behind him](https://faceless.so/images/models/gpt-image-2-5-sample.webp)

Made by Faceless with GPT Image 2.5 on the studio's kie route: 2K, 9:16, first try. Prompt: "Photoreal vertical film still: an old fisherman mending a green net on a wooden dock at dawn, mist on the water behind him, warm low side light on his hands and weathered face, gulls far off, 35mm lens, shallow depth of field, natural skin texture."

## GPT Image 2.5 or GPT Image 2: which to use

-   **GPT Image 2.5** for photoreal people and places, and for long art direction. It costs 1 credit a picture at 1K and takes about 60s.
-   **GPT Image 2** when you want several takes at once: up to 4 pictures in one run, at a low, medium or high quality step.

**Write the brief like a photographer's note.** GPT Image reads full sentences well, so describe the scene the way you would brief a person: who, where, the light, the lens, the mood.

## What GPT Image costs: 1 to 5 credits a picture

GPT Image credits a picture, by size or quality

Version

Credits a picture

Shapes

Reference pictures

Pictures a run

GPT Image 2.5

1K 1 · 2K 2 · 4K 2

1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9

up to 16

1

GPT Image 2

Low 1 · Medium 2 · High 5

1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16

up to 10

up to 4

Credits come with every plan. Starter is $29 a month for 500 credits, about 250 GPT Image 2.5 pictures at 2K. See [pricing](https://faceless.so/pricing) for the other plans.

## Where GPT Image runs in Faceless

1.  **Open the Text to Image studio.** Open [Text to Image](https://faceless.so/text-to-image) and pick GPT Image 2.5 or GPT Image 2 in the Model menu. The box above opens it with GPT Image already picked.
2.  **Write the brief, add reference pictures if you have them**, and pick the size or quality and the shape.
3.  **Make it.** The credit price shows before you start. To turn a picture into video, add it as the first frame of a [Seedance 2.5](https://faceless.so/models/seedance) clip in Text to Video.

GPT Image 2.5 also works behind the scenes: when a Text to Video clip stars one of your saved [characters](https://faceless.so/characters), it draws the opening still that keeps their face the same.

## How to write a GPT Image prompt

-   **Lead with the subject and the action.** "An old fisherman mending a green net", then the place and the time of day.
-   **Then the camera.** Lens, framing and depth of field: "35mm, shallow depth of field, vertical".
-   **Then the light.** "Warm low side light on his hands" does more than "beautiful lighting".
-   **Ask for texture.** "Natural skin texture" keeps people from looking airbrushed.

## When another model fits better

For pictures built around words, such as thumbnails and posters, use [Nano Banana Pro](https://faceless.so/models/nano-banana), which places and spells text best. Both are in the same studio menu.

## GPT Image questions

Versions, editing, sizes and credits

### What is GPT Image 2?

GPT Image is OpenAI's image model, offered to apps through OpenAI's API. It turns a written brief into a picture and is strongest on long, detailed instructions: who is in the scene, how it is framed, the light, and any words to render. Faceless runs GPT Image 2.5 and GPT Image 2.

### Is GPT Image 2 free on Faceless?

Signing up is free, but making a picture uses credits, which come with a plan (from $29 a month for 500 credits on Starter). A GPT Image 2.5 picture is 1 credit at 1K and 2 at 4K; GPT Image 2 is 1 to 5 credits by quality.

### What is the difference between GPT Image 2.5 and GPT Image 2?

GPT Image 2.5 is the newer model: photoreal people, sets and lighting, 1K to 4K, up to 16 reference pictures, one picture a run, in about a minute. GPT Image 2 picks a quality step (low, medium, high) instead of a size and can make up to 4 pictures in one run.

### Can GPT Image edit my own picture?

Yes. Add reference pictures in the Text to Image studio (up to 16 on GPT Image 2.5, 10 on GPT Image 2) and describe what to change or keep. Faceless uses the same model to keep a saved character's face the same in its video clips.

### Is this the same as making pictures in ChatGPT?

Both come from OpenAI; here the model is called through OpenAI's API instead of the chat. In the studio you also pick the exact size and shape, add up to 16 reference pictures, apply style presets, and use any picture as the first frame of a video clip.

## Other models in Faceless

[Seedance 2.5 and 2.0 ByteDance's video model with sound made in the same pass.](https://faceless.so/models/seedance)

[Kling 3.0 and 2.5 Turbo Photoreal people and 1080p motion from Kuaishou.](https://faceless.so/models/kling)

[Veo 3.1 and Veo 3.1 Fast Google's video model with dialogue and sound design.](https://faceless.so/models/veo)

[Nano Banana Pro and Nano Banana 2 Google's image model that spells text right.](https://faceless.so/models/nano-banana)

## Ready to Create Your Own Videos?

Start creating amazing AI-powered faceless videos in minutes with Faceless

[Start my channel](https://faceless.so/projects)[View Pricing](https://faceless.so/pricing)

Free to sign upPlans from $29/moCancel anytime
