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/Direct Inversion+Pix2Pix-Zero

Direct Inversion+Pix2Pix-Zero

Reported on 16 benchmarks across 4 tasks · 1 paper

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

Audio8 results

10-shot image generationonPIE-Bench
Background LPIPS· 2023-10-02
138.98
best: 9.92 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
10-shot image generationonPIE-Bench
Background PSNR· 2023-10-02
21.53
best: 35.87 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
10-shot image generationonPIE-Bench
CLIPSIM· 2023-10-02
23.31
best: 27.33 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
10-shot image generationonPIE-Bench
Structure Distance· 2023-10-02
49.22
best: 70.9 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
1 Image, 2*2 StitchionPIE-Bench
Background LPIPS· 2023-10-02
138.98
best: 9.92 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
1 Image, 2*2 StitchionPIE-Bench
Background PSNR· 2023-10-02
21.53
best: 35.87 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
1 Image, 2*2 StitchionPIE-Bench
CLIPSIM· 2023-10-02
23.31
best: 27.33 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
1 Image, 2*2 StitchionPIE-Bench
Structure Distance· 2023-10-02
49.22
best: 70.9 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506

Medical4 results

Image GenerationonPIE-Bench
Background LPIPS· 2023-10-02
138.98
best: 9.92 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
Image GenerationonPIE-Bench
Background PSNR· 2023-10-02
21.53
best: 35.87 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
Image GenerationonPIE-Bench
CLIPSIM· 2023-10-02
23.31
best: 27.33 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
Image GenerationonPIE-Bench
Structure Distance· 2023-10-02
49.22
best: 70.9 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506

Natural Language Processing4 results

Text-to-Image GenerationonPIE-Bench
Background LPIPS· 2023-10-02
138.98
best: 9.92 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
Text-to-Image GenerationonPIE-Bench
Background PSNR· 2023-10-02
21.53
best: 35.87 (KV-Edit)
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
Text-to-Image GenerationonPIE-Bench
CLIPSIM· 2023-10-02
23.31
best: 27.33 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506
Text-to-Image GenerationonPIE-Bench
Structure Distance· 2023-10-02
49.22
best: 70.9 (FireFlow (Add Q))
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code arXiv:2310.01506