Which AI Image Generator Has the Best Character Consistency? OpenAI vs Gemini vs Black Forest Labs vs Runway (May 2026) | Tech Stackups

Skip to main content

Note: This article was originally published using OpenAI's gpt-image-1. It has been updated to use gpt-image-2.

FLUX.2 and Gemini 3.1 Flash produce the strongest character consistency across our three tests. gpt-image-2 comes in third and Runway Gen-4 last.

Character consistency is one of the hardest problems in AI image generation. Getting a model to place the same person in a new scene without their features drifting is something users expect and models regularly fail at.

We ran three tests across four models to find out which handles this best:

Can it place a real person in a new scene without changing their features?

Can it add clothing items to an image while preserving every other detail?

Can it generate a stylized character consistently across six independent frames?

You can find all the test code in our GitHub repository.

Results at a glance​

FLUX.2 and Gemini 3.1 Flash produced the strongest character consistency across our three tests. Here is how all four models compare.

Placing the same person in a new scene​

We gave each model a reference photo of a real person and asked it to place them in a new scene as a coffee shop barista, without changing their features.

Winner: FLUX.2​

FLUX.2 and Gemini both passed this test. Here is a side-by-side of the best result:

Loser: Runway​

Runway failed this test. Here is the result:

Adding items to an image while preserving every other detail​

We gave each model a reference photo of a person alongside three clothing items and asked it to place all three items on the person without changing anything else.

Winner: FLUX.2​

FLUX.2 was the clear winner, placing all three items with near-perfect accuracy:

Loser: Runway​

Runway struggled with item accuracy and character consistency:

Generating a stylized character consistently across multiple images​

We gave each model a pixel art sprite and asked it to generate six independent frames of a walk cycle, each with a different pose, with no chaining between frames.

Winner: Gemini 3.1 Flash​

Gemini 3.1 Flash showed the most consistent character style across all six frames:

Loser: Runway Gen-4​

Runway generated characters that were inconsistent both with the reference and with each other:

Comparing FLUX.2, Gemini 3.1 Flash, gpt-image-2, and Runway Gen-4​

Each of the four models takes a different approach to multi-reference image generation. Here is how they compare at a high level.

ModelProviderApproachMax referencesFLUX.2Black Forest LabsMulti-reference synthesis8 via APIGemini 3.1 FlashGoogleMulti-reference inferenceUp to 14gpt-image-2OpenAIMulti-reference inference (image edits endpoint)Up to 16Gen-4RunwayReference-based inference3<br>Full feature comparison​

Here is a full breakdown of how each model differs on API approach, output sizes, pricing, and SDK support.

FLUX.2Gemini 3.1 Flashgpt-image-2Runway Gen-4ProviderBlack Forest LabsGoogleOpenAIRunwayAPI approachSubmit request, poll for resultSynchronous (response in single call)Synchronous (response in single call)Submit request, poll for resultMax reference images8 via API, 10 in playgroundUp to 14Up to 163Output sizesUp to 4MP, any aspect ratio512px, 1K, 2K, 4K1024x1024, 1024x1536, 1536x1024720p or 1080pPrice per image (standard)From $0.03 ([pro]) to $0.07 ([max]) per MP~$0.045 (512px) to ~$0.151 (4K) per image$0.006 (low) to $0.211 (high) per 1024x1024$0.05 (720p) or $0.08 (1080p) per imageSDK / authREST API, API key in headerGoogle GenAI SDK (Python/JS), API keyOpenAI SDK (Python/JS), API keyRunway SDK (Python/JS), API keyAsync / pollingYes, polling requiredNoNoYes, polling required<br>Which model can place the same person in a new scene without changing their features?​

Maintaining a consistent character is both a huge problem with AI image generators as well as a huge expectation from their users, especially with human subjects.

A successful character-consistent image requires two things:

The unique qualities of the subject don't drift away in the new generation.

Their features don't move into the uncanny valley, where they seem slightly off in general.

For this test, we use this reference photo of a human subject with distinct features that we can use to easily track consistency across image generation:

An upside down rose tattoo on the subject's right cheek

A sunflower tattoo on the subject's right arm

Short green hair

Thanks Megan Ruth for the photo.

We placed the subject in a completely different scene for these tests. Specifically, as a barista in a coffee shop.

FLUX.2​

FLUX.2 uses multi-reference synthesis, where you pass a reference image directly as input_image alongside a text prompt.

The model uses this as a character reference and generates a new scene while preserving the subject's identity.

# Encode the reference photo as base64 — this becomes the...