# Controllable Image Generation on 5,000-image Reconstruction (evaluation)

Source: [Controllable Image Generation on 5,000-image Reconstruction (evaluation)](<https://www.sota2.com/research/sota/controllable-image-generation-on-5-000-image-reconstruction-evaluation>)

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

Data updated: 2026-02-26T05:44:43.880Z

Evaluation of models performing controllable image generation tasks using the 5,000-image Reconstruction dataset, assessed via FID, LPIPS, SSIM, and PSNR metrics.

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 | Controllable Image Generation |
| Dataset (including any stated split) | 5,000-image Reconstruction (evaluation) |
| 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/controllable-image-generation-on-5-000-image-reconstruction-evaluation.md?metric=FID>): Lower is better; unit: SCALAR.

- [LPIPS](<https://www.sota2.com/research/sota/controllable-image-generation-on-5-000-image-reconstruction-evaluation.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/controllable-image-generation-on-5-000-image-reconstruction-evaluation.md?metric=SSIM>): Higher is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/controllable-image-generation-on-5-000-image-reconstruction-evaluation.md?metric=PSNR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Vec2Pix | 15.52 | Not recorded | 6993f64c9ebc499c97409cf0 |
| Vec2Pix | 16.03 | Not recorded | 6993f64c9ebc499c97409cf0 |
| Canny | 17.38 | Not recorded | 6993f64c9ebc499c97409cf0 |
| Segmentation Mask | 17.75 | Not recorded | 6993f64c9ebc499c97409cf0 |
| Depth | 19.65 | Not recorded | 6993f64c9ebc499c97409cf0 |
| Stroke | 22.42 | Not recorded | 6993f64c9ebc499c97409cf0 |

### Vec2Pix

FID: 15.52. Result ID: 699a97895698665ec422c050.

[Reporting paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

Recorded evaluation configuration: {"Representation":"SVG","NPV":true,"Base Model":"FLUX.1"}. This record does not assert independent reproduction.

### Vec2Pix

FID: 16.03. Result ID: 699a97895698665ec422c04f.

[Reporting paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

Recorded evaluation configuration: {"Representation":"SVG","NPV":false,"Base Model":"FLUX.1"}. This record does not assert independent reproduction.

### Canny

FID: 17.38. Result ID: 699a97895698665ec422c04b.

[Reporting paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018f.md>)

Recorded evaluation configuration: {"Representation":"Canny","Base Model":"FLUX.1"}. This record does not assert independent reproduction.

### Segmentation Mask

FID: 17.75. Result ID: 699a97895698665ec422c04e.

[Reporting paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f0a1e209131cea437f2.md>)

[Implementation](<https://segment-anything.com/>)

Recorded evaluation configuration: {"Representation":"Segmentation Mask","Base Model":"FLUX.1"}. This record does not assert independent reproduction.

### Depth

FID: 19.65. Result ID: 699a97895698665ec422c04c.

[Reporting paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ef1e209131cea8018f.md>)

Recorded evaluation configuration: {"Representation":"Depth","Base Model":"FLUX.1"}. This record does not assert independent reproduction.

### Stroke

FID: 22.42. Result ID: 699a97895698665ec422c04d.

[Reporting paper](<https://www.sota2.com/research/paper/6993f64c9ebc499c97409cf0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b831e209131cea2ebbb.md>)

Recorded evaluation configuration: {"Representation":"Stroke","Base Model":"FLUX.1"}. This record does not assert independent reproduction.

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