# Conditional Image Generation on ImageNet 100

Source: [Conditional Image Generation on ImageNet 100](<https://www.sota2.com/research/sota/conditional-image-generation-on-imagenet-100>)

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

Data updated: 2026-07-07T10:22:06.281Z

Evaluation of conditional image generation models using the ImageNet 100 subset, reporting quality metrics like FID and KID.

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 | Conditional Image Generation |
| Dataset (including any stated split) | ImageNet 100 |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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/conditional-image-generation-on-imagenet-100.md?metric=FID>): Lower is better; unit: SCALAR.

- [KID](<https://www.sota2.com/research/sota/conditional-image-generation-on-imagenet-100.md?metric=KID>): Lower is better; unit: SCALAR.

- [Percentage Change](<https://www.sota2.com/research/sota/conditional-image-generation-on-imagenet-100.md?metric=Percentage%20Change>): Lower is better; unit: PERCENT.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| MoEMA | 11.747 | Not recorded | 6a4c882e85dba69fef8b2b7d |
| StaticMA | 11.802 | Not recorded | 6a4c882e85dba69fef8b2b7d |
| BestSingle | 13.021 | Not recorded | 6a4c882e85dba69fef8b2b7d |
| SimpleAvg | 17.889 | Not recorded | 6a4c882e85dba69fef8b2b7d |

### MoEMA

FID: 11.747. Result ID: 6a4cd33a60b88bb339ca783e.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: {"Condition representation":"CLIP text encoder"}. This record does not assert independent reproduction.

### StaticMA

FID: 11.802. Result ID: 6a4cd33a60b88bb339ca783d.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BestSingle

FID: 13.021. Result ID: 6a4cd33a60b88bb339ca783b.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SimpleAvg

FID: 17.889. Result ID: 6a4cd33a60b88bb339ca783c.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882e85dba69fef8b2b7d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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