# Subject-driven Text-to-Image Generation on DreamBooth 30 subjects

Source: [Subject-driven Text-to-Image Generation on DreamBooth 30 subjects](<https://www.sota2.com/research/sota/subject-driven-text-to-image-generation-on-dreambooth-30-subjects>)

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

Data updated: 2026-02-26T06:04:52.861Z

Evaluation of Subject-driven Text-to-Image generation models using the DreamBooth 30 subjects dataset, assessed via Subject Fidelity and Prompt Fidelity 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 | Subject-driven Text-to-Image Generation |
| Dataset (including any stated split) | DreamBooth 30 subjects |
| Metric | Subject Fidelity |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Subject Fidelity](<https://www.sota2.com/research/sota/subject-driven-text-to-image-generation-on-dreambooth-30-subjects.md?metric=Subject%20Fidelity>): Higher is better; unit: PERCENT.

- [Prompt Fidelity](<https://www.sota2.com/research/sota/subject-driven-text-to-image-generation-on-dreambooth-30-subjects.md?metric=Prompt%20Fidelity>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Subject Fidelity | Result date | Report paper |
| --- | --- | --- | --- |
| DreamBooth | 68 | Not recorded | 68fa6ec31e209131cea41d81 |
| Textual Inversion | 22 | Not recorded | 68fa6ec31e209131cea41d81 |

### DreamBooth

Subject Fidelity: 68. Result ID: 69903e073a6c314849ff2e75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41d81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41d81.md>)

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

Recorded evaluation configuration: {"Backbone":"Stable Diffusion"}. This record does not assert independent reproduction.

### Textual Inversion

Subject Fidelity: 22. Result ID: 69903e073a6c314849ff2e76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ec31e209131cea41d81.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d2d1e209131cea38190.md>)

Recorded evaluation configuration: {"Backbone":"Stable Diffusion"}. This record does not assert independent reproduction.

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