# latent-guided image synthesis on AFHQ

Source: [latent-guided image synthesis on AFHQ](<https://www.sota2.com/research/sota/latent-guided-image-synthesis-on-afhq>)

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

Data updated: 2026-02-26T05:44:11.214Z

Evaluation of models performing latent-guided image synthesis on the AFHQ dataset, typically measured using generative quality metrics like FID and perceptual similarity metrics like LPIPS.

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 | latent-guided image synthesis |
| Dataset (including any stated split) | AFHQ |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/latent-guided-image-synthesis-on-afhq.md?metric=FID>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/latent-guided-image-synthesis-on-afhq.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Real images | 12.9 | Not recorded | 68fa676c1e209131cea1603b |
| StarGAN v2 | 16.2 | Not recorded | 68fa676c1e209131cea1603b |
| MUNIT | 41.5 | Not recorded | 68fa676c1e209131cea1603b |
| MSGAN | 61.4 | Not recorded | 68fa676c1e209131cea1603b |
| DRIT | 95.6 | Not recorded | 68fa676c1e209131cea1603b |

### Real images

FID: 12.9. Result ID: 698d32d08b517eb4331fbb73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

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

### StarGAN v2

FID: 16.2. Result ID: 698d32d08b517eb4331fbb72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

[Implementation](<https://github.com/clovaai/stargan-v2>)

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

### MUNIT

FID: 41.5. Result ID: 698d32d08b517eb4331fbb6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64c01e209131cea06469.md>)

[Implementation](<https://github.com/nvlabs/MUNIT>)

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

### MSGAN

FID: 61.4. Result ID: 698d32d08b517eb4331fbb71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bf1e209131cea0c1ec.md>)

[Implementation](<https://github.com/HelenMao/MSGAN/>)

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

### DRIT

FID: 95.6. Result ID: 698d32d08b517eb4331fbb70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1603b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64aa1e209131cea05f9e.md>)

[Implementation](<https://github.com/HsinYingLee/DRIT/>)

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.