# Sketch-to-Image Generation on Sketchy In the Wild

Source: [Sketch-to-Image Generation on Sketchy In the Wild](<https://www.sota2.com/research/sota/sketch-to-image-generation-on-sketchy-in-the-wild>)

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

Data updated: 2026-02-26T05:44:44.864Z

Evaluation of models performing Sketch-to-Image Generation on the Sketchy In the Wild dataset, assessed using metrics including FID, GlobalCLIP, LocalCLIP, VQAScore, L-VQAScore, 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 Generation |
| Dataset (including any stated split) | Sketchy In the Wild |
| 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-generation-on-sketchy-in-the-wild.md?metric=FID>): Lower is better; unit: SCALAR.

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

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

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

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

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

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| IP-Adapter | 1.16 | Not recorded | 699bdef709c33900fcd80458 |
| LOTS\* | 1.19 | Not recorded | 699bdef709c33900fcd80458 |
| LOTS | 1.23 | Not recorded | 699bdef709c33900fcd80458 |
| ControlNet | 1.24 | Not recorded | 699bdef709c33900fcd80458 |
| ControlNet | 1.37 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-ControlNet | 1.37 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-ControlNet | 1.37 | Not recorded | 699bdef709c33900fcd80458 |
| AnyControl | 1.41 | Not recorded | 699bdef709c33900fcd80458 |
| SD | 1.46 | Not recorded | 699bdef709c33900fcd80458 |
| SDXL | 1.46 | Not recorded | 699bdef709c33900fcd80458 |
| GLIGEN | 1.57 | Not recorded | 699bdef709c33900fcd80458 |
| GLIGEN | 1.58 | Not recorded | 699bdef709c33900fcd80458 |
| T2I-Adapter | 1.6 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-T2I-Adapter | 1.72 | Not recorded | 699bdef709c33900fcd80458 |
| T2I-Adapter | 2.54 | Not recorded | 699bdef709c33900fcd80458 |
| Multi-T2I-Adapter | 2.64 | Not recorded | 699bdef709c33900fcd80458 |
| IP-Adapter | 2.75 | Not recorded | 699bdef709c33900fcd80458 |

### IP-Adapter

FID: 1.16. Result ID: 699d0a205698665ec4aa2867.

[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: {"Conditioning (Visual/Textual)":"G/G","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### LOTS\*

FID: 1.19. Result ID: 699d0a205698665ec4aa286a.

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

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

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

### LOTS

FID: 1.23. Result ID: 699d0a205698665ec4aa286b.

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

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

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

### ControlNet

FID: 1.24. Result ID: 699d0a205698665ec4aa2865.

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

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

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

### ControlNet

FID: 1.37. Result ID: 699d0a205698665ec4aa285e.

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

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

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

### Multi-ControlNet

FID: 1.37. Result ID: 699d0a205698665ec4aa285f.

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

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

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

### Multi-ControlNet

FID: 1.37. Result ID: 699d0a205698665ec4aa2866.

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

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

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

### AnyControl

FID: 1.41. Result ID: 699d0a205698665ec4aa2863.

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

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

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

### SD

FID: 1.46. Result ID: 699d0a205698665ec4aa285b.

[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: {"Conditioning (Visual/Textual)":"-/G","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### SDXL

FID: 1.46. Result ID: 699d0a205698665ec4aa285c.

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

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

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

### GLIGEN

FID: 1.57. Result ID: 699d0a205698665ec4aa285d.

[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: {"Conditioning (Visual/Textual)":"-/L","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### GLIGEN

FID: 1.58. Result ID: 699d0a205698665ec4aa2864.

[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: {"Conditioning (Visual/Textual)":"-/L","Evaluation Protocol":"Fine-tuned"}. This record does not assert independent reproduction.

### T2I-Adapter

FID: 1.6. Result ID: 699d0a205698665ec4aa2868.

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

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

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

### Multi-T2I-Adapter

FID: 1.72. Result ID: 699d0a205698665ec4aa2869.

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

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

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

### T2I-Adapter

FID: 2.54. Result ID: 699d0a205698665ec4aa2861.

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

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

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

### Multi-T2I-Adapter

FID: 2.64. Result ID: 699d0a205698665ec4aa2862.

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

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

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

### IP-Adapter

FID: 2.75. Result ID: 699d0a205698665ec4aa2860.

[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: {"Conditioning (Visual/Textual)":"G/G","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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