TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

Models/TextDiffuser2

TextDiffuser2

Reported on 10 benchmarks across 1 task · 1 paper · 8 SOTA

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

Medical10 results

  • Image GenerationonTextAtlasEval
    StyledTextSynth Clip Score· 2023-11-28
    0.251
    best: 0.2938 (Grok3)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    StyledTextSynth FID· 2023-11-28
    114.31
    best: 71.09 (SD3.5 Large)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    StyledTextSynth OCR (Accuracy)· 2023-11-28
    0.76
    best: 30.58 (Dalle3)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    StyledTextSynth OCR (F1 Score)· 2023-11-28
    1.46
    best: 38.25 (Dalle3)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    TextScenesHQ Clip Score· 2023-11-28
    0.2252
    best: 0.3367 (Dalle3)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    TextScenesHQ FID· 2023-11-28
    84.1
    best: 64.44 (SD3.5 Large)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    TextScenesHQ OCR (Accuracy)· 2023-11-28
    0.66
    best: 69.26 (Dalle3)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    TextScenesHQ OCR (F1 Score)· 2023-11-28
    1.25
    best: 51.63 (Dalle3)
    SOTA
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    StyledTextSynth OCR (Cer)· 2023-11-28
    0.99
    best: 0.73 (Grok3)
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465
  • Image GenerationonTextAtlasEval
    TextScenesHQ OCR (Cer)· 2023-11-28
    0.96
    best: 0.57 (Grok3)
    TextDiffuser-2: Unleashing the Power of Language Models for Text RenderingarXiv:2311.16465