Why GemClean? A side-by-side test on a public Gemini image dataset
Getting rid of the bright sparkle is only half the job. We looked at what four tools left behind in the same corner of each JPEG.
What we found
GemClean scored higher than all three other tools on 12 of 20 images. It scored higher on 13 against GeminiWatermark.io and on 13 against GeminiWatermarkRemover.io. Gradually AI returned no result for 3 inputs.
GeminiWatermarkRemover.io scored below 3 on 16 images. GemClean scored below 3 on 6. A score of 3 means the crop showed no readily visible residue or new artifact.
The difference was easy to spot on a blue-gray reflection. On an image with two overlapping sparkles, all four tools left a visible mark.
The team behind GemClean ran this comparison.
A sparkle over a reflection
The three browser tools leave a recognizable outline on the water. GemClean leaves a much fainter trace.





Matched 256 × 256 crops. Original from Goku OpenLab.
See the tied result and the overlapping sparkles
A textured wall
All four results earned the same score. Some leave a faint outline in the stone, while GemClean slightly softens the texture.





Matched 256 × 256 crops. Original from Goku OpenLab.
Two overlapping sparkles
Every tool leaves a visible mark. GemClean reduces the larger shape, while the second sparkle remains.





Matched 256 × 256 crops. Original from Goku OpenLab.
How we ran the test
We drew candidates in a fixed random order from three folders of the Goku OpenLab Nano Banana Pro dataset. We selected 20 JPEGs with visible corner sparkles by inspecting the inputs. The same files went to three standalone tools we found in a desktop Google search for gemini watermark remover. Each site describes its method as reverse alpha blending. We used each site’s standard workflow.
We ran the same P20 model used by GemClean locally in FP32 at the service’s 256 × 256 crop size. Codex scored matching crops, with tool names hidden and the order shuffled for each image. Some images had appeared in earlier testing. The 0–3 scale assessed visible residue and changes to nearby detail.
A tie means two outputs fell in the same grade. We used files as published and could not verify their export history or whether they were disjoint from training data. The scores describe these 20 JPEGs from one collection.
See all 20 scores, the scoring scale, and downloads
| Compared with | GemClean higher | Same score | GemClean lower |
|---|---|---|---|
| GeminiWatermark.io | 13 | 7 | 0 |
| GeminiWatermarkRemover.io | 13 | 7 | 0 |
| Gradually AI | 18 | 2 | 0 |
Scoring scale
- 3 — No readily visible residue or new artifact
- 2 — Faint residue or small local change
- 1 — Obvious residue or new artifact
- 0 — No result or major visible defect
| Source image | GemClean | GeminiWatermark.io | GeminiWatermarkRemover.io | Gradually AI |
|---|---|---|---|---|
| NB_10220_0 | 3 | 1 | 1 | 1 |
| NB_10369_0 | 1 | 0 | 0 | 0 |
| NB_10081_0 | 3 | 2 | 2 | 2 |
| NB_10049_0 | 3 | 3 | 3 | 1 |
| NB_10020_0 | 3 | 1 | 3 | 0 No result |
| NB_10338_0 | 3 | 2 | 2 | 1 |
| NB_15562_0 | 3 | 1 | 1 | 1 |
| NB_15807_0 | 2 | 2 | 2 | 0 No result |
| NB_15188_0 | 3 | 1 | 1 | 1 |
| NB_15773_0 | 2 | 2 | 0 | 0 |
| NB_15003_0 | 3 | 1 | 1 | 1 |
| NB_20273_0 | 2 | 0 | 0 | 0 No result |
| NB_20632_0 | 2 | 2 | 2 | 2 |
| NB_20450_0 | 3 | 1 | 1 | 2 |
| NB_20528_0 | 3 | 3 | 3 | 3 |
| NB_20869_0 | 3 | 2 | 2 | 2 |
| NB_15386_0 | 3 | 1 | 1 | 1 |
| NB_10458_0 | 2 | 2 | 2 | 0 |
| NB_15288_0 | 3 | 3 | 3 | 2 |
| NB_10413_0 | 3 | 0 | 1 | 1 |
GemClean checkpoint pass020-980caaf7-fp32-v1. Model weights are private. The JSON includes SHA-256 hashes and links to the pinned dataset revision.
Inputs by Goku OpenLab under CC BY 4.0. The figures show cropped inputs and tool outputs.
Try GemClean on your image