whatmodel.sh / image / Imagen 4 Fast
Imagen 4 Fast
↗ share
+ contribute
Imagen 4 Fast is a closed-weights image model from Google, released August 2025. Licence: proprietary.
Catalogue identity notes
Google's Imagen 4 Fast, model id imagen-4.0-fast-generate-001 (GA 14 Aug 2025 per the Vertex AI model page). Rapidata's 6M text-to-image dataset lists 'Imagen 4 Fast' (Google) separately from 'Imagen 4' and 'Imagen 4 Ultra' (both catalogued); the Face Generation Benchmark uses the Replicate id 'google/imagen-4-fast'. Distinct from imagen-4 and imagen-4-ultra. Retired: Google's own model page lists a discontinuation date of 30 Jun 2026 (pricing page still showed $0.02 on 2026-10-10), so no current run option is listed.
Model information sources
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Imagen 4 Fast, out of 197 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 89 |  Step1X-Edit v1.2 | 53±2 | local | ||
| 90 |  Kling Image 2.1 | 53±7 | api $0.014/image | ||
| 91 | Imagen 4 Fast | 53±4 | comparison only | ||
| 92 |  Wan 2.5 Image-to-Image Preview | 53±4 | api $0.030/image | ||
| 93 |  MiniMax image-01 | 53±5 | api $0.0035/image | ||
| more from Google | |||||
| 5 | Nano Banana 2.1 | 81±2 | api $0.034/image | ||
| 9 | Nano Banana 2 (Gemini 3.1 Flash Image) | 76±1 | api $0.067/image | ||
| 10 | Nano Banana Pro (Gemini 3 Pro Image) | 76±1 | api $0.13/image | ||
$ what it's good at
other tests2 not in a task · 94% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata human-face generation alignment (Elo) | 1027.7 ✎ | ▃··▅▃··▃▃··█ beats 4/8 | 58% |
| Rapidata Benchmark.ai image benchmark (overall Elo) | 930.2 ✎ | ▁▁▁▄▂█▂▁▁▂▁▁ beats 7/34 | 35% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Rapidata/Face_Generation_Benc… 58%, Rapidata/text-to-image-human-… 35%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Rapidata/Face_Generation_Benchmark (Human Face Generation Alignment) published dataset-card leaderboard | 1 | 58% |
| Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings | 1 | 35% |
| prior · pull toward the middle | 6% | |
| weighted average | = 52.9 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json