# Text-and-Visual-to-Image Generation (Style Transfer) on CelebA TV2I 1.0 (test val)

Source: [Text-and-Visual-to-Image Generation (Style Transfer) on CelebA TV2I 1.0 (test val)](<https://www.sota2.com/research/sota/text-and-visual-to-image-generation-style-transfer-on-celeba-tv2i-1-0-test-val>)

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

Data updated: 2026-05-08T08:07:17.717Z

Evaluation of models performing Text-and-Visual-to-Image Generation, specifically focusing on Style Transfer capabilities, using the test/validation split of the CelebA TV2I 1.0 dataset. Metrics include ID-Distance and Face Detection Rate.

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-and-Visual-to-Image Generation (Style Transfer) |
| Dataset (including any stated split) | CelebA TV2I 1.0 (test val) |
| Metric | ID Distance |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [ID Distance](<https://www.sota2.com/research/sota/text-and-visual-to-image-generation-style-transfer-on-celeba-tv2i-1-0-test-val.md?metric=ID%20Distance>): Lower is better; unit: SCALAR.

- [Face Detection Rate](<https://www.sota2.com/research/sota/text-and-visual-to-image-generation-style-transfer-on-celeba-tv2i-1-0-test-val.md?metric=Face%20Detection%20Rate>): Higher is better; unit: PERCENT.

- [Condition Consistency](<https://www.sota2.com/research/sota/text-and-visual-to-image-generation-style-transfer-on-celeba-tv2i-1-0-test-val.md?metric=Condition%20Consistency>): Higher is better; unit: PERCENT.

- [General Fidelity](<https://www.sota2.com/research/sota/text-and-visual-to-image-generation-style-transfer-on-celeba-tv2i-1-0-test-val.md?metric=General%20Fidelity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ID Distance | Result date | Report paper |
| --- | --- | --- | --- |
| SOW | 0.8068 | Not recorded | 68fa75e11e209131cea6a68f |
| SOW | 0.8089 | Not recorded | 68fa75e11e209131cea6a68f |
| SOW | 0.8239 | Not recorded | 68fa75e11e209131cea6a68f |
| SOW | 0.8515 | Not recorded | 68fa75e11e209131cea6a68f |

### SOW

ID Distance: 0.8068. Result ID: 69fd993b47f34ce924e0745c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

Recorded evaluation configuration: {"Adaptive Position (AP)":true,"Dynamic Attention Modulation (DAM)":true,"Prompt Intensification (PI)":true}. This record does not assert independent reproduction.

### SOW

ID Distance: 0.8089. Result ID: 69fd993b47f34ce924e0745b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

Recorded evaluation configuration: {"Adaptive Position (AP)":true,"Dynamic Attention Modulation (DAM)":true,"Prompt Intensification (PI)":false}. This record does not assert independent reproduction.

### SOW

ID Distance: 0.8239. Result ID: 69fd993b47f34ce924e0745a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

Recorded evaluation configuration: {"Adaptive Position (AP)":true,"Dynamic Attention Modulation (DAM)":false,"Prompt Intensification (PI)":false}. This record does not assert independent reproduction.

### SOW

ID Distance: 0.8515. Result ID: 69fd993b47f34ce924e07459.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75e11e209131cea6a68f.md>)

Recorded evaluation configuration: {"Adaptive Position (AP)":false,"Dynamic Attention Modulation (DAM)":false,"Prompt Intensification (PI)":false}. This record does not assert independent reproduction.

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