# Sketch-conditioned Image Generation on MS-COCO 2017

Source: [Sketch-conditioned Image Generation on MS-COCO 2017](<https://www.sota2.com/research/sota/sketch-conditioned-image-generation-on-ms-coco-2017>)

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

Data updated: 2026-06-23T07:53:56.902Z

Evaluation of models performing image generation conditioned on input sketches using the MS-COCO 2017 dataset, assessed using FID and CLIP 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 | Sketch-conditioned Image Generation |
| Dataset (including any stated split) | MS-COCO 2017 |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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-conditioned-image-generation-on-ms-coco-2017.md?metric=FID>): Lower is better; unit: SCALAR.

- [CLIP Score](<https://www.sota2.com/research/sota/sketch-conditioned-image-generation-on-ms-coco-2017.md?metric=CLIP%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| UNITY\_Pre | 21.98 | Not recorded | 6a3a131a206542251d7c7028 |
| UNITY\_Ind | 23.89 | Not recorded | 6a3a131a206542251d7c7028 |
| ControlNet++ | 25.43 | Not recorded | 6a3a131a206542251d7c7028 |
| ControlNet | 25.87 | Not recorded | 6a3a131a206542251d7c7028 |
| T2I-Adapter | 27.64 | Not recorded | 6a3a131a206542251d7c7028 |

### UNITY\_Pre

FID: 21.98. Result ID: 6a3a3b8bfbc373592c343b8d.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

Recorded evaluation configuration: {"Params (M)":"384.83","FLOPs (G)":"140.17","Backbone":"SDXL"}. This record does not assert independent reproduction.

### UNITY\_Ind

FID: 23.89. Result ID: 6a3a3b8bfbc373592c343b8c.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

Recorded evaluation configuration: {"Params (M)":"384.83","FLOPs (G)":"140.17","Backbone":"SDXL"}. This record does not assert independent reproduction.

### ControlNet++

FID: 25.43. Result ID: 6a3a3b8bfbc373592c343b8b.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75c71e209131cea69ed4.md>)

Recorded evaluation configuration: {"Params (M)":"1250.98","FLOPs (G)":"1336.69","Backbone":"SDXL"}. This record does not assert independent reproduction.

### ControlNet

FID: 25.87. Result ID: 6a3a3b8bfbc373592c343b89.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

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

Recorded evaluation configuration: {"Params (M)":"1250.98","FLOPs (G)":"1336.69","Backbone":"SDXL"}. This record does not assert independent reproduction.

### T2I-Adapter

FID: 27.64. Result ID: 6a3a3b8bfbc373592c343b8a.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a131a206542251d7c7028.md>)

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

Recorded evaluation configuration: {"Params (M)":"79.03","FLOPs (G)":"29.95","Backbone":"SDXL"}. This record does not assert independent reproduction.

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