{"task":"Image Editing","dataset":"ImgEdit-Data","metric_names":["Overall","Add","Adjust","Extract","Replace","Remove","Background","Style"],"rows":[{"id":132045,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"BAGEL-NHR-EDIT","metrics":{"Action":"3.95","Add":"4.19","Adjust":"3.55","Background":"3.42","Extract":"1.62","Hybrid":"2.94","Overall":"3.39","Remove":"3.18","Replace":"3.77","Style":"4.3"},"paper_url":"https://arxiv.org/abs/2507.14119v1","paper_title":"NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining","paper_date":"2025-07-18","code_links":[],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":1,"source":"archive","tags":[]},{"id":132046,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"UniWorld-V1","metrics":{"Action":"2.74","Add":"3.82","Adjust":"3.64","Background":"2.99","Extract":"2.27","Hybrid":"2.96","Overall":"3.26","Remove":"3.24","Replace":"3.47","Style":"4.21"},"paper_url":"https://arxiv.org/abs/2506.03147v3","paper_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","paper_date":"2025-06-03","code_links":[{"title":"PKU-YuanGroup/UniWorld-V1","url":"https://github.com/PKU-YuanGroup/UniWorld-V1"},{"title":"pku-yuangroup/imgedit","url":"https://github.com/pku-yuangroup/imgedit"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132047,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"BAGEL","metrics":{"Action":"4.17","Add":"3.56","Adjust":"3.31","Background":"3.24","Extract":"1.70","Hybrid":"2.38","Overall":"3.20","Remove":"2.62","Replace":"3.30","Style":"4.49"},"paper_url":"https://arxiv.org/abs/2505.14683v1","paper_title":"Emerging Properties in Unified Multimodal Pretraining","paper_date":"2025-05-20","code_links":[{"title":"ByteDance-Seed/Bagel","url":"https://github.com/ByteDance-Seed/Bagel"},{"title":"neverbiasu/ComfyUI-BAGEL","url":"https://github.com/neverbiasu/ComfyUI-BAGEL"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132048,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"Step1X-Edit","metrics":{"Action":"2.52","Add":"3.88","Adjust":"3.14","Background":"3.16","Extract":"1.76","Hybrid":"2.64","Overall":"3.06","Remove":"2.41","Replace":"3.40","Style":"4.63"},"paper_url":"https://arxiv.org/abs/2504.17761v3","paper_title":"Step1X-Edit: A Practical Framework for General Image Editing","paper_date":"2025-04-24","code_links":[{"title":"stepfun-ai/step1x-edit","url":"https://github.com/stepfun-ai/step1x-edit"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132049,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"ICEdit","metrics":{"Action":"3.68","Add":"3.58","Adjust":"3.39","Background":"3.08","Extract":"1.73","Hybrid":"2.04","Overall":"3.05","Remove":"2.93","Replace":"3.15","Style":"3.84"},"paper_url":"https://arxiv.org/abs/2406.11194v4","paper_title":"In-Context Editing: Learning Knowledge from Self-Induced Distributions","paper_date":"2024-06-17","code_links":[{"title":"bigai-ai/ICE","url":"https://github.com/bigai-ai/ICE"},{"title":"EVOKE-LMM/EVOKE","url":"https://github.com/EVOKE-LMM/EVOKE"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132050,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"UltraEdit","metrics":{"Action":"2.98","Add":"3.44","Adjust":"2.81","Background":"2.83","Extract":"2.13","Hybrid":"1.91","Overall":"2.70","Remove":"1.45","Replace":"2.96","Style":"3.76"},"paper_url":"https://arxiv.org/abs/2407.05282v2","paper_title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","paper_date":"2024-07-07","code_links":[{"title":"pkunlp-icler/ultraedit","url":"https://github.com/pkunlp-icler/ultraedit"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132051,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"AnyEdit","metrics":{"Action":"2.65","Add":"3.18","Adjust":"2.95","Background":"2.24","Extract":"1.88","Hybrid":"1.56","Overall":"2.45","Remove":"2.23","Replace":"2.47","Style":"2.85"},"paper_url":"https://arxiv.org/abs/2502.05628v2","paper_title":"AnyEdit: Edit Any Knowledge Encoded in Language Models","paper_date":"2025-02-08","code_links":[],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132052,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"Instruct-Pix2Pix","metrics":{"Action":"1.46","Add":"2.45","Adjust":"1.83","Background":"1.44","Extract":"1.44","Hybrid":"1.2","Overall":"1.88","Remove":"1.50","Replace":"2.01","Style":"3.55"},"paper_url":"https://arxiv.org/abs/2211.09800v2","paper_title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","paper_date":"2022-11-17","code_links":[{"title":"huggingface/diffusers","url":"https://github.com/huggingface/diffusers"},{"title":"timothybrooks/instruct-pix2pix","url":"https://github.com/timothybrooks/instruct-pix2pix"},{"title":"mv-lab/InstructIR","url":"https://github.com/mv-lab/InstructIR"},{"title":"lsl001006/zone","url":"https://github.com/lsl001006/zone"},{"title":"xuduo35/InstructPix2Pix","url":"https://github.com/xuduo35/InstructPix2Pix"},{"title":"mahdip72/InstructPix2Pix","url":"https://github.com/mahdip72/InstructPix2Pix"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":132053,"task":"Image Editing","parent_task":null,"dataset":"ImgEdit-Data","model_name":"MagicBrush","metrics":{"Action":"1.22","Add":"2.84","Adjust":"1.58","Background":"1.75","Extract":"1.51","Hybrid":"1.62","Overall":"1.83","Remove":"1.58","Replace":"1.97","Style":"2.38"},"paper_url":"https://arxiv.org/abs/2306.10012v3","paper_title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","paper_date":"2023-06-16","code_links":[{"title":"osu-nlp-group/magicbrush","url":"https://github.com/osu-nlp-group/magicbrush"}],"metrics_order":"[\"Overall\", \"Add\", \"Adjust\", \"Extract\", \"Replace\", \"Remove\", \"Background\", \"Style\", \"Hybrid\", \"Action\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}