# Text-guided Image Generation on MS-COCO 512 x 512 v1.4 (val)

Source: [Text-guided Image Generation on MS-COCO 512 x 512 v1.4 (val)](<https://www.sota2.com/research/sota/text-guided-image-generation-on-ms-coco-512-x-512-v1-4-val>)

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

Data updated: 2026-04-23T09:49:06.366Z

Evaluation of Text-guided Image Generation models using FID, sFID, and CLIP Score metrics on the MS-COCO 512x512 v1.4 validation set.

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 Generation |
| Dataset (including any stated split) | MS-COCO 512 x 512 v1.4 (val) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 6 of 6 |
| 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-generation-on-ms-coco-512-x-512-v1-4-val.md?metric=FID>): Lower is better; unit: SCALAR.

- [sFID](<https://www.sota2.com/research/sota/text-guided-image-generation-on-ms-coco-512-x-512-v1-4-val.md?metric=sFID>): Lower is better; unit: SCALAR.

- [CLIP Score](<https://www.sota2.com/research/sota/text-guided-image-generation-on-ms-coco-512-x-512-v1-4-val.md?metric=CLIP%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| SA-PTQ | 13.1 | Not recorded | 68fa78661e209131cea7836b |
| SA-QLoRA | 13.27 | Not recorded | 68fa78661e209131cea7836b |
| Q-Diffusion | 13.28 | Not recorded | 68fa78661e209131cea7836b |
| EfficientDM | 13.31 | Not recorded | 68fa78661e209131cea7836b |
| PTQD | 13.65 | Not recorded | 68fa78661e209131cea7836b |
| Q-Diffusion | 14.4 | Not recorded | 68fa78661e209131cea7836b |

### SA-PTQ

FID: 13.1. Result ID: 69e9eb0047f34ce924d18730.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

Recorded evaluation configuration: {"W/A":"8/8","TBOPs":"51.8"}. This record does not assert independent reproduction.

### SA-QLoRA

FID: 13.27. Result ID: 69e9eb0047f34ce924d18733.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

Recorded evaluation configuration: {"W/A":"4/8","TBOPs":"25.9"}. This record does not assert independent reproduction.

### Q-Diffusion

FID: 13.28. Result ID: 69e9eb0047f34ce924d1872e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f9e1e209131cea46a5b.md>)

Recorded evaluation configuration: {"W/A":"8/8","TBOPs":"51.8"}. This record does not assert independent reproduction.

### EfficientDM

FID: 13.31. Result ID: 69e9eb0047f34ce924d18732.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d91e209131cea58e33.md>)

Recorded evaluation configuration: {"W/A":"4/8","TBOPs":"25.9"}. This record does not assert independent reproduction.

### PTQD

FID: 13.65. Result ID: 69e9eb0047f34ce924d1872f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec51e209131cea41ea8.md>)

[Implementation](<https://github.com/42Shawn/PTQ4DM>)

Recorded evaluation configuration: {"W/A":"8/8","TBOPs":"51.8"}. This record does not assert independent reproduction.

### Q-Diffusion

FID: 14.4. Result ID: 69e9eb0047f34ce924d18731.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78661e209131cea7836b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f9e1e209131cea46a5b.md>)

Recorded evaluation configuration: {"W/A":"4/8","TBOPs":"25.9"}. This record does not assert independent reproduction.

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