# Text-Guided Image Manipulation on Multi-Modal CelebA-HQ Open-Text

Source: [Text-Guided Image Manipulation on Multi-Modal CelebA-HQ Open-Text](<https://www.sota2.com/research/sota/text-guided-image-manipulation-on-multi-modal-celeba-hq-open-text>)

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

Data updated: 2026-02-26T05:44:12.883Z

Evaluation of text-guided image manipulation models using the Open-Text subset of the Multi-Modal CelebA-HQ dataset, assessed via FID, accuracy, and realism scores.

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 | text-guided image manipulation |
| Dataset (including any stated split) | Multi-Modal CelebA-HQ Open-Text |
| 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/text-guided-image-manipulation-on-multi-modal-celeba-hq-open-text.md?metric=FID>): Lower is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/text-guided-image-manipulation-on-multi-modal-celeba-hq-open-text.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Realism Score](<https://www.sota2.com/research/sota/text-guided-image-manipulation-on-multi-modal-celeba-hq-open-text.md?metric=Realism%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| TediGAN-B | 107.32 | Not recorded | 68fa69cf1e209131cea24435 |
| TediGAN-A | 113.57 | Not recorded | 68fa69cf1e209131cea24435 |
| ManiGAN | 141.51 | Not recorded | 68fa69cf1e209131cea24435 |

### TediGAN-B

FID: 107.32. Result ID: 698de781ffc3901de0997ab1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69cf1e209131cea24435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cf1e209131cea24435.md>)

[Implementation](<https://github.com/weihaox/TediGAN>)

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

### TediGAN-A

FID: 113.57. Result ID: 698de781ffc3901de0997ab0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69cf1e209131cea24435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cf1e209131cea24435.md>)

[Implementation](<https://github.com/weihaox/TediGAN>)

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

### ManiGAN

FID: 141.51. Result ID: 698de781ffc3901de0997aaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69cf1e209131cea24435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673e1e209131cea15268.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.