Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SANA-1.5 4.8B

SANA-1.5 4.8B

Reported on 12 benchmarks across 4 tasks · 1 paper · 8 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio6 results

10-shot image generationonGenEval
Single Obj.· 2025-01-30
0.99
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
10-shot image generationonGenEval
Two Obj.· 2025-01-30
0.85
best: 0.94 (MindOmni)
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
1 Image, 2*2 StitchionGenEval
Single Obj.· 2025-01-30
0.99
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
1 Image, 2*2 StitchionGenEval
Two Obj.· 2025-01-30
0.85
best: 0.94 (MindOmni)
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
10-shot image generationonGenEval
Overall· 2025-01-30
0.72
best: 0.95 (SD3.5-Medium+Flow-GRPO)
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
1 Image, 2*2 StitchionGenEval
Overall· 2025-01-30
0.72
best: 0.95 (SD3.5-Medium+Flow-GRPO)
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427

Medical3 results

Image GenerationonGenEval
Single Obj.· 2025-01-30
0.99
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
Image GenerationonGenEval
Two Obj.· 2025-01-30
0.85
best: 0.94 (MindOmni)
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
Image GenerationonGenEval
Overall· 2025-01-30
0.72
best: 0.95 (SD3.5-Medium+Flow-GRPO)
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427

Natural Language Processing3 results

Text-to-Image GenerationonGenEval
Single Obj.· 2025-01-30
0.99
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
Text-to-Image GenerationonGenEval
Two Obj.· 2025-01-30
0.85
best: 0.94 (MindOmni)
SOTA
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427
Text-to-Image GenerationonGenEval
Overall· 2025-01-30
0.72
best: 0.95 (SD3.5-Medium+Flow-GRPO)
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer arXiv:2501.18427