# Image Generation on ImageNet-LT (50k samples)

Source: [Image Generation on ImageNet-LT (50k samples)](<https://www.sota2.com/research/sota/image-generation-on-imagenet-lt-50k-samples>)

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

Data updated: 2026-02-26T05:44:23.139Z

Evaluation of image generation models using the ImageNet-LT dataset variant, which contains 50,000 samples, typically assessed using metrics like FID, IS, F\_beta, 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-LT (50k samples) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| 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-lt-50k-samples.md?metric=FID>): Lower is better; unit: SCALAR.

- [F\_beta](<https://www.sota2.com/research/sota/image-generation-on-imagenet-lt-50k-samples.md?metric=F_beta>): Higher is better; unit: SCALAR.

- [Recall](<https://www.sota2.com/research/sota/image-generation-on-imagenet-lt-50k-samples.md?metric=Recall>): Higher is better; unit: SCALAR.

- [IS](<https://www.sota2.com/research/sota/image-generation-on-imagenet-lt-50k-samples.md?metric=IS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| CB-DDPM | 16.3 | Not recorded | 68fa6fb71e209131cea4701b |
| DDPM | 17.4 | Not recorded | 68fa6fb71e209131cea4701b |

### CB-DDPM

FID: 16.3. Result ID: 6990e7e83a6c314849042ef0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea4701b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea4701b.md>)

[Implementation](<https://github.com/qym7/CBDM-pytorch>)

Recorded evaluation configuration: {"guidance strength (omega)":1.6,"regularization weight (tau)":0.01}. This record does not assert independent reproduction.

### DDPM

FID: 17.4. Result ID: 6990e7e83a6c314849042eef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea4701b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68ef1e209131cea1f0d5.md>)

[Implementation](<https://github.com/hojonathanho/diffusion>)

Recorded evaluation configuration: {"guidance strength (omega)":1.2,"regularization weight (tau)":null}. This record does not assert independent reproduction.

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