# Sketch-to-image on Sketchy (test)

Source: [Sketch-to-image on Sketchy (test)](<https://www.sota2.com/research/sota/sketch-to-image-on-sketchy-test>)

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

Data updated: 2026-02-26T05:44:44.847Z

Evaluation of Sketch-to-image performance on the test split of the Sketchy dataset, assessed using metrics such as FID, CLIP scores, and SSIM.

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 | Sketch-to-image |
| Dataset (including any stated split) | Sketchy (test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 17 of 17 |
| 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/sketch-to-image-on-sketchy-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [GlobalCLIP Score](<https://www.sota2.com/research/sota/sketch-to-image-on-sketchy-test.md?metric=GlobalCLIP%20Score>): Higher is better; unit: SCALAR.

- [LocalCLIP Score](<https://www.sota2.com/research/sota/sketch-to-image-on-sketchy-test.md?metric=LocalCLIP%20Score>): Higher is better; unit: SCALAR.

- [VQAScore](<https://www.sota2.com/research/sota/sketch-to-image-on-sketchy-test.md?metric=VQAScore>): Higher is better; unit: SCALAR.

- [L-VQAScore](<https://www.sota2.com/research/sota/sketch-to-image-on-sketchy-test.md?metric=L-VQAScore>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/sketch-to-image-on-sketchy-test.md?metric=SSIM>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| LOTS | 0.74 | Not recorded | 699bdef709c33900fcd80458 |
| IP-Adapter | 0.75 | Not recorded | 699bdef709c33900fcd80458 |
| LOTS\* | 0.79 | Not recorded | 699bdef709c33900fcd80458 |
| ControlNet | 0.82 | Not recorded | 699bdef709c33900fcd80458 |
| ControlNet | 0.96 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-ControlNet | 0.96 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-ControlNet | 0.98 | Not recorded | 699bdef709c33900fcd80458 |
| SD | 1.03 | Not recorded | 699bdef709c33900fcd80458 |
| AnyControl | 1.06 | Not recorded | 699bdef709c33900fcd80458 |
| SDXL | 1.09 | Not recorded | 699bdef709c33900fcd80458 |
| GLIGEN | 1.1 | Not recorded | 699bdef709c33900fcd80458 |
| GLIGEN | 1.12 | Not recorded | 699bdef709c33900fcd80458 |
| T2I-Adapter | 1.25 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-T2I-Adapter | 1.36 | Not recorded | 699bdef709c33900fcd80458 |
| T2I-Adapter | 2.03 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-T2I-Adapter | 2.25 | Not recorded | 699bdef709c33900fcd80458 |
| IP-Adapter | 2.48 | Not recorded | 699bdef709c33900fcd80458 |

### LOTS

FID: 0.74. Result ID: 699d0a205698665ec4aa285a.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

Recorded evaluation configuration: {"Training Protocol":"Proposed (Current)","Conditioning (Visual/Textual)":"Local/Local"}. This record does not assert independent reproduction.

### IP-Adapter

FID: 0.75. Result ID: 699d0a205698665ec4aa2856.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70591e209131cea4a798.md>)

[Implementation](<https://ip-adapter.github.io/>)

Recorded evaluation configuration: {"Training Protocol":"Fine-tuned","Conditioning (Visual/Textual)":"Global/Global"}. This record does not assert independent reproduction.

### LOTS\*

FID: 0.79. Result ID: 699d0a205698665ec4aa2859.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b251e209131cea86d5d.md>)

Recorded evaluation configuration: {"Training Protocol":"Proposed (Prior)","Conditioning (Visual/Textual)":"Local/Local"}. This record does not assert independent reproduction.

### ControlNet

FID: 0.82. Result ID: 699d0a205698665ec4aa2854.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"Training Protocol":"Fine-tuned","Conditioning (Visual/Textual)":"Global/Global"}. This record does not assert independent reproduction.

### ControlNet

FID: 0.96. Result ID: 699d0a205698665ec4aa284d.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"Global/Global"}. This record does not assert independent reproduction.

### Multi-ControlNet

FID: 0.96. Result ID: 699d0a205698665ec4aa2855.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"Training Protocol":"Fine-tuned","Conditioning (Visual/Textual)":"Local/Global"}. This record does not assert independent reproduction.

### Multi-ControlNet

FID: 0.98. Result ID: 699d0a205698665ec4aa284e.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71481e209131cea50695.md>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"Local/Global"}. This record does not assert independent reproduction.

### SD

FID: 1.03. Result ID: 699d0a205698665ec4aa284a.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c391e209131cea32e4a.md>)

[Implementation](<https://github.com/CompVis/latent-diffusion>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"None/Global"}. This record does not assert independent reproduction.

### AnyControl

FID: 1.06. Result ID: 699d0a205698665ec4aa2852.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ffa9.md>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"Local/Global"}. This record does not assert independent reproduction.

### SDXL

FID: 1.09. Result ID: 699d0a205698665ec4aa284b.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70011e209131cea487fb.md>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"None/Global"}. This record does not assert independent reproduction.

### GLIGEN

FID: 1.1. Result ID: 699d0a205698665ec4aa284c.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43bdf.md>)

[Implementation](<https://gligen.github.io/>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"None/Local"}. This record does not assert independent reproduction.

### GLIGEN

FID: 1.12. Result ID: 699d0a205698665ec4aa2853.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f131e209131cea43bdf.md>)

[Implementation](<https://gligen.github.io/>)

Recorded evaluation configuration: {"Training Protocol":"Fine-tuned","Conditioning (Visual/Textual)":"None/Local"}. This record does not assert independent reproduction.

### T2I-Adapter

FID: 1.25. Result ID: 699d0a205698665ec4aa2857.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea42531.md>)

Recorded evaluation configuration: {"Training Protocol":"Fine-tuned","Conditioning (Visual/Textual)":"Global/Global"}. This record does not assert independent reproduction.

### Multi-T2I-Adapter

FID: 1.36. Result ID: 699d0a205698665ec4aa2858.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea42531.md>)

Recorded evaluation configuration: {"Training Protocol":"Fine-tuned","Conditioning (Visual/Textual)":"Local/Global"}. This record does not assert independent reproduction.

### T2I-Adapter

FID: 2.03. Result ID: 699d0a205698665ec4aa2850.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea42531.md>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"Global/Global"}. This record does not assert independent reproduction.

### Multi-T2I-Adapter

FID: 2.25. Result ID: 699d0a205698665ec4aa2851.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea42531.md>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"Local/Global"}. This record does not assert independent reproduction.

### IP-Adapter

FID: 2.48. Result ID: 699d0a205698665ec4aa284f.

[Reporting paper](<https://www.sota2.com/research/paper/699bdef709c33900fcd80458.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70591e209131cea4a798.md>)

[Implementation](<https://ip-adapter.github.io/>)

Recorded evaluation configuration: {"Training Protocol":"Zero-shot","Conditioning (Visual/Textual)":"Global/Global"}. This record does not assert independent reproduction.

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