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.
FLUX.2 Flex
Combine characters, objects and scenes from multiple reference images.
Pricing details
- Cost is 8.1 credits per megapixel (input + output).
Rated by blind team votes and an AI judge
As of
Score 59 · #4 of 14 in Product photography
90% range 50–69
Score out of 100: how often people would pick this model's output over an average model's on the same tests. 50 is average.
How we score
On product photography: Wins 25 / Losses 15 / Ties 7 from 47 team votes, plus 6 AI judge scores.
Every model runs the same Glif tests. Team members see two outputs side by side without the model names and pick the one that better fits the test, or call it a tie. An AI judge also scores every output from 0 to 10.
A Bradley-Terry fit turns all those head-to-head results into one rating per model. Ties count as half a win, and each AI judge score counts as half a vote.
The score is the predicted chance people prefer this model's output to the average model's on the same board, so 50 is average. A board is one kind of task, like text-to-image. Scores only compare models on the same board.
The 90% range comes from resampling the votes and refitting many times. Overlapping ranges are close to a tie. A model ranks once it has 20 votes' worth of ratings on a board. Until then it shows no score, only how close it is.
Other boards
Brand and text rendering: 57 · #4 of 6
Text-to-image: 34 · #9 of 14
Character consistency: 32 · #15 of 15
Surgical image editing: Needs more ratings (19 of 20)
Image-to-image: Needs more ratings (4 of 20)
Multi-image reference: Needs more ratings (2 of 20)
Test outputs
Compare all modelsFLUX.2 Flex in practice
What it does and when to use it.
Model summary
Flux 2 Flex generates and edits images with flexible aspect ratios. It accepts up to eight reference images to guide composition, subject details, style, and color. It can also create images with text, such as posters, labels, and infographics. Cost depends on whether the request generates a new image or edits an existing one.
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
- High-fidelity text-to-image generation with exact color control
- Image editing/variation (iterating on an existing image)
- Multi-reference guided generation (up to 8 input images in Glif)
- Product/brand visual exploration with consistent visual cues
- Style transfer, including analog/film-grain looks
- Simple text-in-image designs (posters, labels, basic infographic-style images)
- Creating assets in non-square aspect ratios for web/social/print layouts
More from the FLUX.2 family
Explore other options from the same family.
FLUX.2 Pro
Black Forest Labs
A balance of speed and detail for everyday image generation and editing.
FLUX.2 Turbo
Black Forest Labs
Quick drafts, previews and image edits when speed matters most.
Retired
FLUX.2 Klein 9B
Black Forest Labs
Fast image generation with readable text and realistic photos.
Retired
FLUX.2 Max
Black Forest Labs
Detailed photos and precise edits, with web search for current subjects.