HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Text Based Image Editing On Pie Bench

评估指标

Background LPIPS
Background PSNR
CLIPSIM
Structure Distance

评测结果

各个模型在此基准测试上的表现结果

Paper Title
FireFlow (Add Q)239.416.4927.3370.9FireFlow: 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
DDIM Inversion+Pix2Pix-Zero172.2220.4422.8061.68Zero-shot Image-to-Image Translation
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+Plug-and-Play113.4622.2825.4128.22Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
DDIM Inversion+MasaCtrl106.6222.1723.9628.38MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
Direct Inversion+Plug-and-Play106.0622.4625.4124.29Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Direct Inversion+MasaCtrl87.9422.6424.3824.70Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Negative-Prompt Inversion+Prompt-to-Prompt69.0126.2124.6116.17Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models
StyleDiffusion+Prompt-to-Prompt66.1026.0524.7811.65StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
Null-Text Inversion+Prompt-to-Prompt60.6727.0324.7513.44Null-text Inversion for Editing Real Images using Guided Diffusion Models
Virtual Inversion+Prompt-to-Prompt+LCM55.8526.6424.5715.61Inversion-Free Image Editing with Natural Language
Direct Inversion+Prompt-to-Prompt54.5527.2225.0211.65Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Virtual Inversion+Prompt-to-Prompt47.9827.5224.8914.22Inversion-Free Image Editing with Natural Language
Virtual Inversion+Unified Attention Control+LCM47.5828.5125.0313.78Inversion-Free Image Editing with Natural Language
Virtual Inversion+ViMAEdit45.6728.2725.9112.65Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing
KV-Edit9.9235.8725.631.98KV-Edit: Training-Free Image Editing for Precise Background Preservation
0 of 18 row(s) selected.
Text Based Image Editing On Pie Bench | SOTA | HyperAI超神经