# Text-to-image generation on FLUX.1 200 prompts (dev)

Source: [Text-to-image generation on FLUX.1 200 prompts (dev)](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev>)

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

Data updated: 2026-05-27T10:01:05.319Z

Evaluation of Text-to-Image generation models on the specific 200-prompt subset of the FLUX.1 development set, utilizing a comprehensive set of perceptual quality (ImageReward, CLIPScore, FID, PSNR, SSIM, LPIPS) and efficiency metrics (FLOPs, Speed).

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) | FLUX.1 200 prompts (dev) |
| Metric | FLOPs (T) |
| Unit | SIZE |
| Direction | Lower is better |
| Results loaded | 15 of 15 |
| 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

- [FLOPs (T)](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=FLOPs%20(T)>): Lower is better; unit: SIZE.

- [FLOPs Speedup](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=FLOPs%20Speedup>): Higher is better; unit: SCALAR.

- [ImageReward](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=ImageReward>): Higher is better; unit: PERCENT.

- [CLIPScore](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=CLIPScore>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=FID>): Lower is better; unit: SCALAR.

- [PSNR](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-200-prompts-dev.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FLOPs (T) | Result date | Report paper |
| --- | --- | --- | --- |
| TaylorSeer | 595.12 | Not recorded | 6a167accdbd7150506f80213 |
| FORA | 595.12 | Not recorded | 6a167accdbd7150506f80213 |
| SpeCa | 603.44 | Not recorded | 6a167accdbd7150506f80213 |
| SoftCap | 614.55 | Not recorded | 6a167accdbd7150506f80213 |
| SoftCap | 724.62 | Not recorded | 6a167accdbd7150506f80213 |
| SpeCa | 725.58 | Not recorded | 6a167accdbd7150506f80213 |
| FLUX | 743.9 | Not recorded | 6a167accdbd7150506f80213 |
| TaylorSeer | 743.9 | Not recorded | 6a167accdbd7150506f80213 |
| FORA | 743.9 | Not recorded | 6a167accdbd7150506f80213 |
| SoftCap | 917.39 | Not recorded | 6a167accdbd7150506f80213 |
| TaylorSeer | 967.07 | Not recorded | 6a167accdbd7150506f80213 |
| FORA | 967.07 | Not recorded | 6a167accdbd7150506f80213 |
| SpeCa | 967.75 | Not recorded | 6a167accdbd7150506f80213 |
| FLUX | 1859.75 | Not recorded | 6a167accdbd7150506f80213 |
| Full FLUX | 3719.5 | Not recorded | 6a167accdbd7150506f80213 |

### TaylorSeer

FLOPs (T): 595.12. Result ID: 6a16c067fbc373592c10642a.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d54.md>)

Recorded evaluation configuration: {"O":"2","Compute Regime":"Low-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### FORA

FLOPs (T): 595.12. Result ID: 6a16c067fbc373592c10642b.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73f01e209131cea5efba.md>)

Recorded evaluation configuration: {"N":"7","Efficient Attention":"true"}. This record does not assert independent reproduction.

### SpeCa

FLOPs (T): 603.44. Result ID: 6a16c067fbc373592c106429.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b561e209131cea87e41.md>)

Recorded evaluation configuration: {"Compute Regime":"Low-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### SoftCap

FLOPs (T): 614.55. Result ID: 6a16c067fbc373592c10642c.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

Recorded evaluation configuration: {"Compute Regime":"Low-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### SoftCap

FLOPs (T): 724.62. Result ID: 6a16c067fbc373592c106428.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

Recorded evaluation configuration: {"Compute Regime":"Mid-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### SpeCa

FLOPs (T): 725.58. Result ID: 6a16c067fbc373592c106425.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b561e209131cea87e41.md>)

Recorded evaluation configuration: {"Compute Regime":"Mid-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### FLUX

FLOPs (T): 743.9. Result ID: 6a16c067fbc373592c106420.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

Recorded evaluation configuration: {"Steps":"10","Efficient Attention":"true"}. This record does not assert independent reproduction.

### TaylorSeer

FLOPs (T): 743.9. Result ID: 6a16c067fbc373592c106426.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d54.md>)

Recorded evaluation configuration: {"O":"2","Compute Regime":"Mid-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### FORA

FLOPs (T): 743.9. Result ID: 6a16c067fbc373592c106427.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73f01e209131cea5efba.md>)

Recorded evaluation configuration: {"N":"5","Efficient Attention":"true"}. This record does not assert independent reproduction.

### SoftCap

FLOPs (T): 917.39. Result ID: 6a16c067fbc373592c106424.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

Recorded evaluation configuration: {"Compute Regime":"High-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### TaylorSeer

FLOPs (T): 967.07. Result ID: 6a16c067fbc373592c106422.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d54.md>)

Recorded evaluation configuration: {"Compute Regime":"High-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### FORA

FLOPs (T): 967.07. Result ID: 6a16c067fbc373592c106423.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73f01e209131cea5efba.md>)

Recorded evaluation configuration: {"N":"4","Efficient Attention":"true"}. This record does not assert independent reproduction.

### SpeCa

FLOPs (T): 967.75. Result ID: 6a16c067fbc373592c106421.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b561e209131cea87e41.md>)

Recorded evaluation configuration: {"Compute Regime":"High-compute","Efficient Attention":"true"}. This record does not assert independent reproduction.

### FLUX

FLOPs (T): 1859.75. Result ID: 6a16c067fbc373592c10641f.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

Recorded evaluation configuration: {"Steps":"25","Efficient Attention":"true"}. This record does not assert independent reproduction.

### Full FLUX

FLOPs (T): 3719.5. Result ID: 6a16c067fbc373592c10641e.

[Reporting paper](<https://www.sota2.com/research/paper/6a167accdbd7150506f80213.md>)

Recorded evaluation configuration: {"Steps":"50","Efficient Attention":"true"}. This record does not assert independent reproduction.

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