HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Text Based Image Editing On Pie Bench

評価指標

Background LPIPS
Background PSNR
CLIPSIM
Structure Distance

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
Background LPIPS
Background PSNR
CLIPSIM
Structure Distance
Paper TitleRepository
Direct Inversion+MasaCtrl87.9422.6424.3824.70Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Direct Inversion+Pix2Pix-Zero138.9821.5323.3149.22Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
FireFlow123.623.0326.0227.1FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
DDIM Inversion+Prompt-to-Prompt208.8017.8725.0169.43Prompt-to-Prompt Image Editing with Cross Attention Control
Negative-Prompt Inversion+Prompt-to-Prompt69.0126.2124.6116.17Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models-
DDIM Inversion+MasaCtrl106.6222.1723.9628.38MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
Virtual Inversion+Prompt-to-Prompt+LCM55.8526.6424.5715.61Inversion-Free Image Editing with Natural Language
StyleDiffusion+Prompt-to-Prompt66.1026.0524.7811.65StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
Virtual Inversion+Prompt-to-Prompt47.9827.5224.8914.22Inversion-Free Image Editing with Natural Language
DDIM Inversion+Pix2Pix-Zero172.2220.4422.8061.68Zero-shot Image-to-Image Translation
Direct Inversion+Prompt-to-Prompt54.5527.2225.0211.65Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
DDIM Inversion+Plug-and-Play113.4622.2825.4128.22Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
Direct Inversion+Plug-and-Play106.0622.4625.4124.29Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Null-Text Inversion+Prompt-to-Prompt60.6727.0324.7513.44Null-text Inversion for Editing Real Images using Guided Diffusion Models
KV-Edit9.9235.8725.631.98KV-Edit: Training-Free Image Editing for Precise Background Preservation
Virtual Inversion+ViMAEdit45.6728.2725.9112.65Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing
FireFlow (Add Q)239.416.4927.3370.9FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
Virtual Inversion+Unified Attention Control+LCM47.5828.5125.0313.78Inversion-Free Image Editing with Natural Language
0 of 18 row(s) selected.