flux2 logo

FLUX.2 Flex

Use this model

Combine characters, objects and scenes from multiple reference images.

OutputsImage
SpeedMedium
Priceup to 82 credits
CostHigh
ReleasedNov 2025

Glif score

As of

Overall 53 · Score 59 · #8 of 20 in Product photography

Scores combine expert human reviewers, expert AI judges and votes from the wider community, and we rank models on quality, speed and cost. * Early score: needs more ratings.

Other boards

Test outputs

FLUX.2 Flex in practice

What it does and when to use it.

Model summary

FLUX.2 Flex is Black Forest Labs’ FLUX.2 model for multi-image composition and editing. It generates from text or edits with up to 8 reference images, at 64 to 2048 pixels per side, and prompts can name references directly, such as “the person from image 1”. Adjustable steps and guidance give finer control than FLUX.2 Pro. Glif charges per megapixel, counting the output and every reference image.

Capabilities

Text to image
Image to image
Image editing
Multi reference conditioning
Color control
Aspect ratio flexibility
Text rendering in image
Style transfer
High fidelity generation

Suggested use cases

  • Put a person from one image into another scene
  • Composites from up to 8 references
  • Style transfer, including film-grain looks
  • Simple posters and labels with text

More from the FLUX.2 family

Explore other options from the same family.

All the models in one place

Run FLUX.2 Flex and every other model on Glif from one chat. One account, one balance, no API keys to wire up.