FLUX.1 Fill [pro] vs Imagen 3
Newest: Imagen 3 · Widest inputs: FLUX.1 Fill [pro] · Image editing: FLUX.1 Fill [pro]. Not enough arena votes yet for a quality score, so this is a spec comparison.
Black Forest Labs
FLUX.1 Fill [pro]
- Arena—
- From—
- Max size—
Google
Imagen 3
- Arena1,057
- From$0.04/image
- Max size—
Add a model
Make it a three-way comparison.
Where they differ
Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.
- NewestImagen 3FLUX.1 Fill [pro] Oct 1, 2024 · Imagen 3 Oct 15, 2024
- Widest inputsFLUX.1 Fill [pro]FLUX.1 Fill [pro]: Text prompts, Reference images · Imagen 3: Text prompts
- Image editingFLUX.1 Fill [pro]Takes a reference image as input: FLUX.1 Fill [pro] yes · Imagen 3 no
- Self-hostingNo confirmed open weightsNo downloadable weights are documented here
- Most API hostsSame reachFLUX.1 Fill [pro]: 1 · Imagen 3: 1
Every spec in one table
Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Quality (blind human votes) | ||
| Text to image arenaElo-style score · higher is better | — | 1,057 ±3#65 of 82 · 359,756 votes |
| Price | ||
| Starting price | — | $0.04/image standard |
| How it is billed | — | Per image |
| Output | ||
| Produces | Images | Images |
| Inputs | ||
| Text prompts | Yes | Yes |
| Reference images (editing) | Yes | No |
| Access | ||
| Weights | Proprietary | Proprietary |
| API hosts | 1 | 1 |
| Released | Oct 1, 2024 | Oct 15, 2024 |
Which should you choose?
Which is better, FLUX.1 Fill [pro] or Imagen 3?
Neither model has enough arena votes for a reliable quality score yet, so this page compares specs only. Run the same three or four prompts through each and judge the results.
Which is cheaper?
Imagen 3 costs from $0.04/image (standard). FLUX.1 Fill [pro] has no published per-image price. Prices are list rates and change often; check the lab before budgeting.
What is the difference between FLUX.1 Fill [pro] and Imagen 3?
FLUX.1 Fill [pro] is an image model from Black Forest Labs (Oct 1, 2024), taking text prompts and reference images and producing images. Imagen 3 is an image model from Google (Oct 15, 2024), taking text prompts and producing images.
Which is newer?
FLUX.1 Fill [pro] Oct 1, 2024; Imagen 3 Oct 15, 2024.
Which can edit an existing image?
Takes a reference image as input: FLUX.1 Fill [pro] yes; Imagen 3 no.
Can I run any of these on my own hardware?
No confirmed open weights. No downloadable weights are documented here.