# Generative Modeling on ImageNet 512x512 (train)

Source: [Generative Modeling on ImageNet 512x512 (train)](<https://www.sota2.com/research/sota/generative-modeling-on-imagenet-512x512-train>)

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

Data updated: 2026-06-05T09:12:46.027Z

Evaluation of generative models on the training split of ImageNet rendered at 512x512 resolution, measured using metrics such as FID, 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 | Generative Modeling |
| Dataset (including any stated split) | ImageNet 512x512 (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/generative-modeling-on-imagenet-512x512-train.md?metric=FID>): Lower is better; unit: SCALAR.

- [IS](<https://www.sota2.com/research/sota/generative-modeling-on-imagenet-512x512-train.md?metric=IS>): Higher is better; unit: SCALAR.

- [Precision](<https://www.sota2.com/research/sota/generative-modeling-on-imagenet-512x512-train.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/generative-modeling-on-imagenet-512x512-train.md?metric=Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| GADC | 6.17 | Not recorded | 6a2258a486173ad9c1468c1f |
| D2C | 14.8 | Not recorded | 6a2258a486173ad9c1468c1f |
| Random | 24.8 | Not recorded | 6a2258a486173ad9c1468c1f |

### GADC

FID: 6.17. Result ID: 6a22930dfbc373592c20eafe.

[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)","Backbone":"DiT-L/2","Training Iterations":"100K","Resolution":"512x512"}. This record does not assert independent reproduction.

### D2C

FID: 14.8. Result ID: 6a22930dfbc373592c20eafd.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a7.md>)

Recorded evaluation configuration: {"Data Budget":"0.8% (10K)","Backbone":"DiT-L/2","Training Iterations":"100K","Resolution":"512x512"}. This record does not assert independent reproduction.

### Random

FID: 24.8. Result ID: 6a22930dfbc373592c20eafc.

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

Recorded evaluation configuration: {"Data Budget":"0.8% (10K)","Backbone":"DiT-L/2","Training Iterations":"100K","Resolution":"512x512"}. This record does not assert independent reproduction.

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