# Unconditional Image Generation on FFHQ 256x256 (train/test)

Source: [Unconditional Image Generation on FFHQ 256x256 (train/test)](<https://www.sota2.com/research/sota/unconditional-image-generation-on-ffhq-256x256-train-test>)

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

Data updated: 2026-02-26T05:44:12.371Z

Evaluation of unconditional image generation models on the combined train and test splits of the FFHQ dataset rendered at 256x256 resolution, typically measured by FID and IS.

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 | Unconditional Image Generation |
| Dataset (including any stated split) | FFHQ 256x256 (train/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/unconditional-image-generation-on-ffhq-256x256-train-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [IS](<https://www.sota2.com/research/sota/unconditional-image-generation-on-ffhq-256x256-train-test.md?metric=IS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| U-Net GAN | 7.48 | Not recorded | 68fa69971e209131cea22eac |
| U-Net GAN | 8.88 | Not recorded | 68fa69971e209131cea22eac |
| BigGAN | 11.48 | Not recorded | 68fa69971e209131cea22eac |
| BigGAN | 14.92 | Not recorded | 68fa69971e209131cea22eac |

### U-Net GAN

FID: 7.48. Result ID: 698dbd8f8b517eb433237158.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Implementation](<https://github.com/boschresearch/unetgan>)

Recorded evaluation configuration: {"Framework":"PyTorch","Resolution":"256x256","Training Iterations":"400k"}. This record does not assert independent reproduction.

### U-Net GAN

FID: 8.88. Result ID: 698dbd8f8b517eb43323715a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Implementation](<https://github.com/boschresearch/unetgan>)

Recorded evaluation configuration: {"Framework":"TensorFlow","Resolution":"256x256","Training Iterations":"400k"}. This record does not assert independent reproduction.

### BigGAN

FID: 11.48. Result ID: 698dbd8f8b517eb433237157.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65661e209131cea0a090.md>)

[Implementation](<https://tfhub.dev/s?q=biggan>)

Recorded evaluation configuration: {"Framework":"PyTorch","Resolution":"256x256","Training Iterations":"400k"}. This record does not assert independent reproduction.

### BigGAN

FID: 14.92. Result ID: 698dbd8f8b517eb433237159.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69971e209131cea22eac.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65661e209131cea0a090.md>)

[Implementation](<https://tfhub.dev/s?q=biggan>)

Recorded evaluation configuration: {"Framework":"TensorFlow","Resolution":"256x256","Training Iterations":"400k"}. This record does not assert independent reproduction.

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