# Unconditional Image Generation on ImageNet (train)

Source: [Unconditional Image Generation on ImageNet (train)](<https://www.sota2.com/research/sota/unconditional-image-generation-on-imagenet-train>)

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

Data updated: 2026-02-26T05:44:10.831Z

Evaluation of unconditional image generation models on the training split of ImageNet, typically measured using FID.

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) | ImageNet (train) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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-imagenet-train.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| BigBiGAN High Res E + SL | 20.32 | Not recorded | 68fa669c1e209131cea11688 |
| BigBiGAN High Res E + SL | 22.34 | Not recorded | 68fa669c1e209131cea11688 |
| BigBiGAN + SL | 22.78 | Not recorded | 68fa669c1e209131cea11688 |

### BigBiGAN High Res E + SL

FID: 20.32. Result ID: 698cfce88b517eb4331e2f8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11688.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11688.md>)

[Implementation](<https://tfhub.dev/s?publisher=deepmind&q=bigbigan>)

Recorded evaluation configuration: {"Steps":"1M","Pseudo-labeling method":"Single Label","Encoder configuration":"High Res E"}. This record does not assert independent reproduction.

### BigBiGAN High Res E + SL

FID: 22.34. Result ID: 698cfce88b517eb4331e2f8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11688.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11688.md>)

[Implementation](<https://tfhub.dev/s?publisher=deepmind&q=bigbigan>)

Recorded evaluation configuration: {"Steps":"500K","Pseudo-labeling method":"Single Label","Encoder configuration":"High Res E"}. This record does not assert independent reproduction.

### BigBiGAN + SL

FID: 22.78. Result ID: 698cfce88b517eb4331e2f8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11688.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea11688.md>)

[Implementation](<https://tfhub.dev/s?publisher=deepmind&q=bigbigan>)

Recorded evaluation configuration: {"Steps":"500K","Pseudo-labeling method":"Single Label","Encoder configuration":"Standard"}. This record does not assert independent reproduction.

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