# Layout-to-image synthesis on MS-COCO (val)

Source: [Layout-to-image synthesis on MS-COCO (val)](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-ms-coco-val>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:38:27.687Z

Evaluation of Layout-to-image synthesis models on the MS-COCO validation set, assessed using metrics like CLIP (local) and IoU (local).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Layout-to-image synthesis |
| Dataset (including any stated split) | MS-COCO (val) |
| Metric | CLIP (local) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [CLIP (local)](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-ms-coco-val.md?metric=CLIP%20(local)>): Higher is better; unit: PERCENT.

- [IoU (local)](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-ms-coco-val.md?metric=IoU%20(local)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CLIP (local) | Result date | Report paper |
| --- | --- | --- | --- |
| Zero-Painter | 26.68 | Not recorded | 68fa738d1e209131cea5d2af |
| MDF | 26.1 | Not recorded | 68fa738d1e209131cea5d2af |
| NTLB | 25.71 | Not recorded | 68fa738d1e209131cea5d2af |
| GLIGEN | 25.52 | Not recorded | 68fa738d1e209131cea5d2af |
| EDIFF-I | 25.3 | Not recorded | 68fa738d1e209131cea5d2af |

### Zero-Painter

CLIP (local): 26.68. Result ID: 6992fef83a6c31484912ef5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d2af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d2af.md>)

[Implementation](<https://github.com/Picsart-AI-Research/Zero-Painter>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MDF

CLIP (local): 26.1. Result ID: 6992fef83a6c31484912ef5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d2af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e8d1e209131cea40872.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NTLB

CLIP (local): 25.71. Result ID: 6992fef83a6c31484912ef59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d2af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386fc.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GLIGEN

CLIP (local): 25.52. Result ID: 6992fef83a6c31484912ef58.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d2af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43bdf.md>)

[Implementation](<https://gligen.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### EDIFF-I

CLIP (local): 25.3. Result ID: 6992fef83a6c31484912ef57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738d1e209131cea5d2af.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eca1e209131cea4229f.md>)

[Implementation](<https://deepimagination.cc/eDiff-I/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.