whatmodel.sh / image / Step1X-Edit v1.2 Preview
Step1X-Edit v1.2 Preview
↗ share
+ contribute
Step1X-Edit v1.2 Preview is an open-weights image model from StepFun, released September 2025. Licence: apache-2.0.
Catalogue identity notes
Comparison-only, proposed so the Step1X-Edit-v1p2 card's GEdit and KRIS runs reach three models (benchmark minimum). The pinned card (@ca85b97) prints own rows for Step1X-Edit v1.1, Step1x-edit-v1p2-preview and Step1x-edit-v1p2 (base/thinking/thinking+reflection). Weights: https://huggingface.co/stepfun-ai/Step1X-Edit-v1p2-preview (sha f77b8edcde2d8fad57e6c515439e1a242e2e748e, created 2025-09-07, apache-2.0, 12,442,484,544 params in safetensors metadata); distinct from the final v1p2 release (catalogue step1x-edit-v1-2).
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Step1X-Edit v1.2 Preview, out of 197 with a score, then more from StepFun.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 101 |  FLUX.1 Kontext [pro] | 50±2 | api $0.040/image | ||
| 102 |  GLM-Image | 50±2 | api $0.015/image +local | ||
| 103 | Step1X-Edit v1.2 Preview | 50±5 | comparison only | ||
| 104 |  Runway Gen-4 Image | 50±3 | api $0.050/image | ||
| 105 |  Lucid Origin | 49±3 | api $0.017/image | ||
| more from StepFun | |||||
| 89 | Step1X-Edit v1.2 | 53±2 | local | ||
| 108 | Step1X-Edit v1.1 | 48±3 | local | ||
| 154 | NextStep-1-Large-Edit | 37±3 | comparison only | ||
$ what it's good at
image to image / editing▁▁▁▃▂▃█▃▃▃▁▁ #60 of 81 * · 91% of its score · 2 tests
Beats GPT Image 1 Mini, FLUX.1 Kontext [pro] here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| KRIS-Bench overall lab | 52.5% ✎ | ██·········█ beats 1/2 | 46% |
| GEdit-Bench overall (G_O, language split unspecified) lab | 74.2% ✎ | █·······█··█ beats 1/2 | 45% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · stepfun-ai/Step1X-Edit-v1p2 m… 91%
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 |
|---|---|---|
 stepfun-ai/Step1X-Edit-v1p2 model card · lab-reported | 2 | 91% |
| prior · pull toward the middle | 9% | |
| weighted average | = 49.9 |
$ 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