# Image Generation on ImageNet condensed 2015 (train)

Source: [Image Generation on ImageNet condensed 2015 (train)](<https://www.sota2.com/research/sota/image-generation-on-imagenet-condensed-2015-train>)

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

Data updated: 2026-06-05T09:12:46.205Z

Evaluation of image generation models on the training split of the ImageNet condensed 2015 dataset, reporting metrics including FID, Inception Score (IS), Precision, and Recall.

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 | Image Generation |
| Dataset (including any stated split) | ImageNet condensed 2015 (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/image-generation-on-imagenet-condensed-2015-train.md?metric=FID>): Lower is better; unit: SCALAR.

- [IS](<https://www.sota2.com/research/sota/image-generation-on-imagenet-condensed-2015-train.md?metric=IS>): Higher is better; unit: SCALAR.

- [Precision](<https://www.sota2.com/research/sota/image-generation-on-imagenet-condensed-2015-train.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/image-generation-on-imagenet-condensed-2015-train.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| GADC | 3.43 | Not recorded | 6a2258a486173ad9c1468c1f |
| K-Medoids† | 4.13 | Not recorded | 6a2258a486173ad9c1468c1f |
| K-Centers† | 39.67 | Not recorded | 6a2258a486173ad9c1468c1f |

### GADC

FID: 3.43. Result ID: 6a22930dfbc373592c20eb43.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a486173ad9c1468c1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2258a486173ad9c1468c1f.md>)

Recorded evaluation configuration: {"Data Budget":"0.8% (10K)","Eval. Samples":"50K","Model Architecture":"DiT-L/2","Resolution":"256 × 256"}. This record does not assert independent reproduction.

### K-Medoids†

FID: 4.13. Result ID: 6a22930dfbc373592c20eb42.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a486173ad9c1468c1f.md>)

Recorded evaluation configuration: {"Data Budget":"0.8% (10K)","Eval. Samples":"50K","Model Architecture":"DiT-L/2","Resolution":"256 × 256","Attachment Phase":"D2C"}. This record does not assert independent reproduction.

### K-Centers†

FID: 39.67. Result ID: 6a22930dfbc373592c20eb41.

[Reporting paper](<https://www.sota2.com/research/paper/6a2258a486173ad9c1468c1f.md>)

Recorded evaluation configuration: {"Data Budget":"0.8% (10K)","Eval. Samples":"50K","Model Architecture":"DiT-L/2","Resolution":"256 × 256","Attachment Phase":"D2C"}. This record does not assert independent reproduction.

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