# Text-to-image Generation on LAION Aesthetics 6.5+ 512x512 zero-shot on MS-COCO V2

Source: [Text-to-image Generation on LAION Aesthetics 6.5+ 512x512 zero-shot on MS-COCO V2](<https://www.sota2.com/research/sota/text-to-image-generation-on-laion-aesthetics-6-5-plus-512x512-zero-shot-on-ms-coco-v2>)

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

Data updated: 2026-05-20T09:14:13.216Z

Evaluation of Text-to-Image generation models using the LAION Aesthetics 6.5+ dataset, specifically under zero-shot conditions at 512x512 resolution, evaluated using prompts derived from MS-COCO V2.

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-image Generation |
| Dataset (including any stated split) | LAION Aesthetics 6.5+ 512x512 zero-shot on MS-COCO V2 |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 12 of 12 |
| 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/text-to-image-generation-on-laion-aesthetics-6-5-plus-512x512-zero-shot-on-ms-coco-v2.md?metric=FID>): Lower is better; unit: SCALAR.

- [IS](<https://www.sota2.com/research/sota/text-to-image-generation-on-laion-aesthetics-6-5-plus-512x512-zero-shot-on-ms-coco-v2.md?metric=IS>): Higher is better; unit: SCALAR.

- [CLIP Score](<https://www.sota2.com/research/sota/text-to-image-generation-on-laion-aesthetics-6-5-plus-512x512-zero-shot-on-ms-coco-v2.md?metric=CLIP%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Teacher | 13.93 | Not recorded | 6a0d4054f984739ed6737b48 |
| LIFT + PLACE | 14.6 | Not recorded | 6a0d4054f984739ed6737b48 |
| LIFT + PLACE | 14.65 | Not recorded | 6a0d4054f984739ed6737b48 |
| BK-SDM | 15.68 | Not recorded | 6a0d4054f984739ed6737b48 |
| BK-SDM | 15.85 | Not recorded | 6a0d4054f984739ed6737b48 |
| BK-SDM | 16.61 | Not recorded | 6a0d4054f984739ed6737b48 |
| LIFT + PLACE | 16.72 | Not recorded | 6a0d4054f984739ed6737b48 |
| Teacher | 20.26 | Not recorded | 6a0d4054f984739ed6737b48 |
| LIFT + PLACE | 20.59 | Not recorded | 6a0d4054f984739ed6737b48 |
| OutKD+FeatKD | 21.17 | Not recorded | 6a0d4054f984739ed6737b48 |
| LIFT + PLACE | 21.21 | Not recorded | 6a0d4054f984739ed6737b48 |
| OutKD+FeatKD | 22.72 | Not recorded | 6a0d4054f984739ed6737b48 |

### Teacher

FID: 13.93. Result ID: 6a0d7a22fbc373592c05b91b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76071e209131cea6b026.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"SD 2.1","Iters":"1620k","MACs":"339.2G","Params":"865.9M"}. This record does not assert independent reproduction.

### LIFT + PLACE

FID: 14.6. Result ID: 6a0d7a22fbc373592c05b921.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"BK-Tiny-v2","Iters":"50k","MACs":"205.3G","Params":"326.8M","K":"16"}. This record does not assert independent reproduction.

### LIFT + PLACE

FID: 14.65. Result ID: 6a0d7a22fbc373592c05b91f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"BK-Small-v2","Iters":"50k","MACs":"218.0G","Params":"485.8M","K":"16"}. This record does not assert independent reproduction.

### BK-SDM

FID: 15.68. Result ID: 6a0d7a22fbc373592c05b920.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76071e209131cea6b026.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"BK-Tiny-v2","Iters":"50k","MACs":"205.3G","Params":"326.8M"}. This record does not assert independent reproduction.

### BK-SDM

FID: 15.85. Result ID: 6a0d7a22fbc373592c05b91c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76071e209131cea6b026.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"BK-Base-v2","Iters":"50k","MACs":"224.1G","Params":"583.5M"}. This record does not assert independent reproduction.

### BK-SDM

FID: 16.61. Result ID: 6a0d7a22fbc373592c05b91e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76071e209131cea6b026.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"BK-Small-v2","Iters":"50k","MACs":"218.0G","Params":"485.8M"}. This record does not assert independent reproduction.

### LIFT + PLACE

FID: 16.72. Result ID: 6a0d7a22fbc373592c05b91d.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Diffusion","Architecture":"BK-Base-v2","Iters":"50k","MACs":"224.1G","Params":"583.5M","K":"16"}. This record does not assert independent reproduction.

### Teacher

FID: 20.26. Result ID: 6a0d7a22fbc373592c05b922.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76071e209131cea6b026.md>)

Recorded evaluation configuration: {"Gen. Type":"Flow","Architecture":"SD 3 (D24)","MACs":"799.24G","Params":"2.03B"}. This record does not assert independent reproduction.

### LIFT + PLACE

FID: 20.59. Result ID: 6a0d7a22fbc373592c05b924.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Flow","Architecture":"SD 3 (D21)","Iters":"50k","MACs":"699.08G","Params":"1.77B","K":"16","Initialization":"ShortGPT \[23\]"}. This record does not assert independent reproduction.

### OutKD+FeatKD

FID: 21.17. Result ID: 6a0d7a22fbc373592c05b923.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Flow","Architecture":"SD 3 (D21)","Iters":"50k","MACs":"699.08G","Params":"1.77B","Initialization":"ShortGPT \[23\]"}. This record does not assert independent reproduction.

### LIFT + PLACE

FID: 21.21. Result ID: 6a0d7a22fbc373592c05b926.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Flow","Architecture":"SD 3 (D18)","Iters":"50k","MACs":"598.83G","Params":"1.52B","K":"16","Initialization":"ShortGPT \[23\]"}. This record does not assert independent reproduction.

### OutKD+FeatKD

FID: 22.72. Result ID: 6a0d7a22fbc373592c05b925.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4054f984739ed6737b48.md>)

Recorded evaluation configuration: {"Gen. Type":"Flow","Architecture":"SD 3 (D18)","Iters":"50k","MACs":"598.83G","Params":"1.52B","Initialization":"ShortGPT \[23\]"}. This record does not assert independent reproduction.

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