# Human Pose Conditioned Image Generation on Single-person images derived from Stable Diffusion XL (val)

Source: [Human Pose Conditioned Image Generation on Single-person images derived from Stable Diffusion XL (val)](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val>)

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

Data updated: 2026-02-26T05:54:19.884Z

Evaluation of models generating human images conditioned on input poses, using the validation split of the dataset derived from Stable Diffusion XL. Metrics focus on training convergence and resource utilization (memory, time).

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 | Human Pose Conditioned Image Generation |
| Dataset (including any stated split) | Single-person images derived from Stable Diffusion XL (val) |
| Metric | Optimizer Memory (GB) |
| 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

- [Optimizer Memory (GB)](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val.md?metric=Optimizer%20Memory%20(GB)>): Lower is better; unit: SIZE.

- [mAP @ 20K steps](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val.md?metric=mAP%20%40%2020K%20steps>): Higher is better; unit: PERCENT.

- [mAP @ 40K steps](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val.md?metric=mAP%20%40%2040K%20steps>): Higher is better; unit: PERCENT.

- [mAP @ 80K steps](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val.md?metric=mAP%20%40%2080K%20steps>): Higher is better; unit: PERCENT.

- [Converged](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val.md?metric=Converged>): Higher is better; unit: SCALAR.

- [Training Time (h) (80K steps)](<https://www.sota2.com/research/sota/human-pose-conditioned-image-generation-on-single-person-images-derived-from-stable-diffusion-xl-val.md?metric=Training%20Time%20(h)%20(80K%20steps)>): Lower is better; unit: TIME.

## Recorded results

| Method | Optimizer Memory (GB) | Result date | Report paper |
| --- | --- | --- | --- |
| COAP | 0.5 | Not recorded | 68fa77641e209131cea73001 |
| COAP | 0.9 | Not recorded | 68fa77641e209131cea73001 |
| COAP | 1 | Not recorded | 68fa77641e209131cea73001 |
| COAP | 1.8 | Not recorded | 68fa77641e209131cea73001 |
| COAP | 1.9 | Not recorded | 68fa77641e209131cea73001 |
| GaLore | 2.3 | Not recorded | 68fa77641e209131cea73001 |
| GaLore | 2.7 | Not recorded | 68fa77641e209131cea73001 |
| GaLore | 3.1 | Not recorded | 68fa77641e209131cea73001 |
| GaLore | 3.1 | Not recorded | 68fa77641e209131cea73001 |
| GaLore | 3.5 | Not recorded | 68fa77641e209131cea73001 |
| COAP | 3.6 | Not recorded | 68fa77641e209131cea73001 |
| Flora | 3.9 | Not recorded | 68fa77641e209131cea73001 |
| GaLore | 4.7 | Not recorded | 68fa77641e209131cea73001 |
| Adafactor | 5.1 | Not recorded | 68fa77641e209131cea73001 |
| AdamW | 9.3 | Not recorded | 68fa77641e209131cea73001 |

### COAP

Optimizer Memory (GB): 0.5. Result ID: 69949cb93a6c3148491e662f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

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

Recorded evaluation configuration: {"Rank Ratio":8,"Optimization Precision":"8-bit"}. This record does not assert independent reproduction.

### COAP

Optimizer Memory (GB): 0.9. Result ID: 69949cb93a6c3148491e662e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

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

Recorded evaluation configuration: {"Rank Ratio":8}. This record does not assert independent reproduction.

### COAP

Optimizer Memory (GB): 1. Result ID: 69949cb93a6c3148491e662b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

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

Recorded evaluation configuration: {"Rank Ratio":4,"Optimization Precision":"8-bit"}. This record does not assert independent reproduction.

### COAP

Optimizer Memory (GB): 1.8. Result ID: 69949cb93a6c3148491e662a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

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

Recorded evaluation configuration: {"Rank Ratio":4}. This record does not assert independent reproduction.

### COAP

Optimizer Memory (GB): 1.9. Result ID: 69949cb93a6c3148491e6627.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

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

Recorded evaluation configuration: {"Rank Ratio":2,"Optimization Precision":"8-bit"}. This record does not assert independent reproduction.

### GaLore

Optimizer Memory (GB): 2.3. Result ID: 69949cb93a6c3148491e662d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56588.md>)

Recorded evaluation configuration: {"Rank Ratio":8,"Optimization Precision":"8-bit"}. This record does not assert independent reproduction.

### GaLore

Optimizer Memory (GB): 2.7. Result ID: 69949cb93a6c3148491e662c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56588.md>)

Recorded evaluation configuration: {"Rank Ratio":8}. This record does not assert independent reproduction.

### GaLore

Optimizer Memory (GB): 3.1. Result ID: 69949cb93a6c3148491e6625.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56588.md>)

Recorded evaluation configuration: {"Rank Ratio":2,"Optimization Precision":"8-bit"}. This record does not assert independent reproduction.

### GaLore

Optimizer Memory (GB): 3.1. Result ID: 69949cb93a6c3148491e6629.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56588.md>)

Recorded evaluation configuration: {"Rank Ratio":4,"Optimization Precision":"8-bit"}. This record does not assert independent reproduction.

### GaLore

Optimizer Memory (GB): 3.5. Result ID: 69949cb93a6c3148491e6628.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56588.md>)

Recorded evaluation configuration: {"Rank Ratio":4}. This record does not assert independent reproduction.

### COAP

Optimizer Memory (GB): 3.6. Result ID: 69949cb93a6c3148491e6626.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

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

Recorded evaluation configuration: {"Rank Ratio":2}. This record does not assert independent reproduction.

### Flora

Optimizer Memory (GB): 3.9. Result ID: 69949cb93a6c3148491e6623.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c24.md>)

Recorded evaluation configuration: {"Rank Ratio":2}. This record does not assert independent reproduction.

### GaLore

Optimizer Memory (GB): 4.7. Result ID: 69949cb93a6c3148491e6624.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea56588.md>)

Recorded evaluation configuration: {"Rank Ratio":2}. This record does not assert independent reproduction.

### Adafactor

Optimizer Memory (GB): 5.1. Result ID: 69949cb93a6c3148491e6622.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64471e209131cea03a91.md>)

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

### AdamW

Optimizer Memory (GB): 9.3. Result ID: 69949cb93a6c3148491e6621.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77641e209131cea73001.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa55761e209131ce9946db.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.
