# Layout-to-image synthesis on COCO-Stuff 256x256 (test)

Source: [Layout-to-image synthesis on COCO-Stuff 256x256 (test)](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-coco-stuff-256x256-test>)

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

Data updated: 2026-02-26T05:44:12.545Z

Evaluation of Layout-to-image synthesis models on the 256x256 test split of the COCO-Stuff dataset, assessed using metrics including Inception Score (IS), FID, and Diversity Score (DS).

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) | COCO-Stuff 256x256 (test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [FID](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-coco-stuff-256x256-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [Inception Score (IS)](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-coco-stuff-256x256-test.md?metric=Inception%20Score%20(IS)>): Higher is better; unit: SCALAR.

- [Diversity Score (DS)](<https://www.sota2.com/research/sota/layout-to-image-synthesis-on-coco-stuff-256x256-test.md?metric=Diversity%20Score%20(DS)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| GauGAN | 22.6 | Not recorded | 68fa699e1e209131cea23203 |
| GauGAN | 41.11 | Not recorded | 68fa699e1e209131cea23203 |
| LostGAN-V2 | 42.55 | Not recorded | 68fa699e1e209131cea23203 |
| LostGAN-V2 | 46.08 | Not recorded | 68fa699e1e209131cea23203 |

### GauGAN

FID: 22.6. Result ID: 698dc7868b517eb43323ad25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699e1e209131cea23203.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11672.md>)

[Implementation](<https://github.com/NVlabs/SPADE>)

Recorded evaluation configuration: {"Mask Source":"Ground Truth (GT)","Resolution":"256x256"}. This record does not assert independent reproduction.

### GauGAN

FID: 41.11. Result ID: 698dc7868b517eb43323ad26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699e1e209131cea23203.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11672.md>)

[Implementation](<https://github.com/NVlabs/SPADE>)

Recorded evaluation configuration: {"Mask Source":"Inferred Masks (by current paper)","Resolution":"256x256"}. This record does not assert independent reproduction.

### LostGAN-V2

FID: 42.55. Result ID: 698dc7868b517eb43323ad27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699e1e209131cea23203.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699e1e209131cea23203.md>)

[Implementation](<https://github.com/iVMCL/LostGANs>)

Recorded evaluation configuration: {"Resolution":"256x256"}. This record does not assert independent reproduction.

### LostGAN-V2

FID: 46.08. Result ID: 698dc7868b517eb43323ad28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699e1e209131cea23203.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699e1e209131cea23203.md>)

[Implementation](<https://github.com/iVMCL/LostGANs>)

Recorded evaluation configuration: {"Resolution":"256x256","Integration":"end-to-end","Additional Component":"SPADE"}. This record does not assert independent reproduction.

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