# Text-to-Object Generation on DreamFusion prompts

Source: [Text-to-Object Generation on DreamFusion prompts](<https://www.sota2.com/research/sota/text-to-object-generation-on-dreamfusion-prompts>)

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

Data updated: 2026-04-21T10:27:42.766Z

Evaluation of Text-to-Object Generation models using the DreamFusion prompt set, assessed via CLIP and ViCLIP image-text similarity 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 | Text-to-Object Generation |
| Dataset (including any stated split) | DreamFusion prompts |
| Metric | CLIP Image-Text Similarity |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [CLIP Image-Text Similarity](<https://www.sota2.com/research/sota/text-to-object-generation-on-dreamfusion-prompts.md?metric=CLIP%20Image-Text%20Similarity>): Higher is better; unit: SCALAR.

- [ViCLIP Image-Text Similarity](<https://www.sota2.com/research/sota/text-to-object-generation-on-dreamfusion-prompts.md?metric=ViCLIP%20Image-Text%20Similarity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CLIP Image-Text Similarity | Result date | Report paper |
| --- | --- | --- | --- |
| UniMesh | 0.296 | Not recorded | 69e704a57d0172140ec7edf4 |
| Flex3D | 0.277 | Not recorded | 69e704a57d0172140ec7edf4 |
| InstantMesh | 0.272 | Not recorded | 69e704a57d0172140ec7edf4 |
| GRM | 0.268 | Not recorded | 69e704a57d0172140ec7edf4 |
| LGM | 0.266 | Not recorded | 69e704a57d0172140ec7edf4 |
| VFusion3D | 0.265 | Not recorded | 69e704a57d0172140ec7edf4 |
| 3DTopia-XL | 0.254 | Not recorded | 69e704a57d0172140ec7edf4 |
| LN3Diff | 0.252 | Not recorded | 69e704a57d0172140ec7edf4 |
| OpenLRM | 0.243 | Not recorded | 69e704a57d0172140ec7edf4 |

### UniMesh

CLIP Image-Text Similarity: 0.296. Result ID: 69e7510c47f34ce924ce3e1f.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Implementation](<https://github.com/AIGeeksGroup/UniMesh>)

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

### Flex3D

CLIP Image-Text Similarity: 0.277. Result ID: 69e7510c47f34ce924ce3e1e.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc13.md>)

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

### InstantMesh

CLIP Image-Text Similarity: 0.272. Result ID: 69e7510c47f34ce924ce3e1a.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72da1e209131cea58e96.md>)

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

### GRM

CLIP Image-Text Similarity: 0.268. Result ID: 69e7510c47f34ce924ce3e1b.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729e1e209131cea57948.md>)

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

### LGM

CLIP Image-Text Similarity: 0.266. Result ID: 69e7510c47f34ce924ce3e19.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72291e209131cea54dd3.md>)

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

### VFusion3D

CLIP Image-Text Similarity: 0.265. Result ID: 69e7510c47f34ce924ce3e18.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74321e209131cea605a6.md>)

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

### 3DTopia-XL

CLIP Image-Text Similarity: 0.254. Result ID: 69e7510c47f34ce924ce3e1d.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

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

### LN3Diff

CLIP Image-Text Similarity: 0.252. Result ID: 69e7510c47f34ce924ce3e1c.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74701e209131cea61cb0.md>)

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

### OpenLRM

CLIP Image-Text Similarity: 0.243. Result ID: 69e7510c47f34ce924ce3e17.

[Reporting paper](<https://www.sota2.com/research/paper/69e704a57d0172140ec7edf4.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.