# Class-conditional image synthesis on ImageNet 256x256 (test)

Source: [Class-conditional image synthesis on ImageNet 256x256 (test)](<https://www.sota2.com/research/sota/class-conditional-image-synthesis-on-imagenet-256x256-test>)

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

Data updated: 2026-02-26T05:44:15.557Z

Evaluation of class-conditional image synthesis models on the test split of the ImageNet dataset rendered at 256x256 resolution, typically measured using FID and Inception Score (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 | Class-conditional image synthesis |
| Dataset (including any stated split) | ImageNet 256x256 (test) |
| 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/class-conditional-image-synthesis-on-imagenet-256x256-test.md?metric=FID>): Lower is better; unit: SCALAR.

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

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| MaskGIT | 4.02 | Not recorded | 68fa6bc61e209131cea303c7 |
| ADM | 4.59 | Not recorded | 68fa6bc61e209131cea303c7 |
| VQGAN | 5.88 | Not recorded | 68fa6bc61e209131cea303c7 |

### MaskGIT

FID: 4.02. Result ID: 698ea2fdffc3901de09f5893.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bc61e209131cea303c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc61e209131cea303c7.md>)

Recorded evaluation configuration: {"Classifier guidance":"0.05 acceptance rate"}. This record does not assert independent reproduction.

### ADM

FID: 4.59. Result ID: 698ea2fdffc3901de09f5891.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bc61e209131cea303c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0e1e209131cea25dba.md>)

[Implementation](<https://github.com/openai/guided-diffusion>)

Recorded evaluation configuration: {"Classifier guidance":"1.0 guidance"}. This record does not assert independent reproduction.

### VQGAN

FID: 5.88. Result ID: 698ea2fdffc3901de09f5892.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bc61e209131cea303c7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a371e209131cea26a4d.md>)

[Implementation](<https://git.io/JnyvK>)

Recorded evaluation configuration: {"Classifier guidance":"0.05 acceptance rate"}. This record does not assert independent reproduction.

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