# Multi-Concept Personalization on Baby+Toy

Source: [Multi-Concept Personalization on Baby+Toy](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy>)

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

Data updated: 2026-02-26T05:46:59.684Z

Evaluation of Multi-Concept Personalization models using the Baby+Toy dataset, assessing image and text alignment scores for individual concepts and overall performance.

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 | Multi-Concept Personalization |
| Dataset (including any stated split) | Baby+Toy |
| Metric | Image Alignment (Mean) |
| Unit | SCALAR |
| Direction | Higher 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

- [Image Alignment (Mean)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Image%20Alignment%20(Mean)>): Higher is better; unit: SCALAR.

- [Text Alignment (Mean)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Text%20Alignment%20(Mean)>): Higher is better; unit: SCALAR.

- [Image Alignment (Combined)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Image%20Alignment%20(Combined)>): Higher is better; unit: SCALAR.

- [Text Alignment (Combined)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Text%20Alignment%20(Combined)>): Higher is better; unit: SCALAR.

- [Image Alignment (Concept1)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Image%20Alignment%20(Concept1)>): Higher is better; unit: SCALAR.

- [Text Alignment (Concept1)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Text%20Alignment%20(Concept1)>): Higher is better; unit: SCALAR.

- [Image Alignment (Concept2)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Image%20Alignment%20(Concept2)>): Higher is better; unit: SCALAR.

- [Text Alignment (Concept2)](<https://www.sota2.com/research/sota/multi-concept-personalization-on-baby-plus-toy.md?metric=Text%20Alignment%20(Concept2)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Image Alignment (Mean) | Result date | Report paper |
| --- | --- | --- | --- |
| DisenDiff | 0.808 | Not recorded | 68fa72dd1e209131cea5906e |
| Custom Diffusion | 0.775 | Not recorded | 68fa72dd1e209131cea5906e |
| DreamBooth | 0.689 | Not recorded | 68fa72dd1e209131cea5906e |
| Textual Inversion | 0.607 | Not recorded | 68fa72dd1e209131cea5906e |

### DisenDiff

Image Alignment (Mean): 0.808. Result ID: 6992a04c3a6c314849103c34.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72dd1e209131cea5906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72dd1e209131cea5906e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Custom Diffusion

Image Alignment (Mean): 0.775. Result ID: 6992a04c3a6c314849103c33.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72dd1e209131cea5906e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcb1e209131cea4771b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DreamBooth

Image Alignment (Mean): 0.689. Result ID: 6992a04c3a6c314849103c32.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72dd1e209131cea5906e.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Textual Inversion

Image Alignment (Mean): 0.607. Result ID: 6992a04c3a6c314849103c31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72dd1e209131cea5906e.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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