{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"Open-MAGVIT2","owner":"TencentARC","isFork":false,"description":"Open-MAGVIT2: Democratizing Autoregressive Visual Generation","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":5,"starsCount":600,"forksCount":21,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-12T09:54:15.087Z"}},{"type":"Public","name":"ST-LLM","owner":"TencentARC","isFork":false,"description":"[ECCV 2024🔥] Official implementation of the paper \"ST-LLM: Large Language Models Are Effective Temporal Learners\"","allTopics":["video-understanding","large-language-models","video-language-model"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":9,"starsCount":104,"forksCount":4,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-09-10T13:25:18.766Z"}},{"type":"Public","name":"mllm-npu","owner":"TencentARC","isFork":false,"description":"mllm-npu: training multimodal large language models on Ascend NPUs","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":77,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-29T02:51:55.863Z"}},{"type":"Public","name":"MasaCtrl","owner":"TencentARC","isFork":false,"description":"[ICCV 2023] Consistent Image Synthesis and Editing","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":21,"starsCount":710,"forksCount":26,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-19T05:56:05.324Z"}},{"type":"Public","name":"Plot2Code","owner":"TencentARC","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":15,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-17T11:49:13.975Z"}},{"type":"Public","name":"PhotoMaker","owner":"TencentARC","isFork":false,"description":"PhotoMaker [CVPR 2024]","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":3,"issueCount":138,"starsCount":9342,"forksCount":745,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-08-15T03:08:03.860Z"}},{"type":"Public","name":"SEED-Story","owner":"TencentARC","isFork":false,"description":"SEED-Story: Multimodal Long Story Generation with Large Language Model","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":7,"starsCount":697,"forksCount":55,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-29T02:47:10.008Z"}},{"type":"Public","name":"MotionCtrl","owner":"TencentARC","isFork":false,"description":"Official Code for MotionCtrl [SIGGRAPH 2024]","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":24,"starsCount":1269,"forksCount":70,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-29T00:04:04.085Z"}},{"type":"Public","name":"GFPGAN","owner":"TencentARC","isFork":false,"description":"GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.","allTopics":["super-resolution","image-restoration","face-restoration","gfpgan","deep-learning","pytorch","gan"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":23,"issueCount":345,"starsCount":35556,"forksCount":5889,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-26T18:44:02.771Z"}},{"type":"Public","name":"CustomNet","owner":"TencentARC","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":6,"starsCount":261,"forksCount":9,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-22T05:11:32.216Z"}},{"type":"Public","name":"BrushNet","owner":"TencentARC","isFork":false,"description":"[ECCV 2024] The official implementation of paper \"BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion\"","allTopics":["text-to-image","image-inpainting","diffusion","eccv","diffusion-models","eccv2024"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":41,"starsCount":1337,"forksCount":112,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-17T11:17:08.571Z"}},{"type":"Public","name":"ViT-Lens","owner":"TencentARC","isFork":false,"description":"[CVPR 2024] ViT-Lens: Towards Omni-modal Representations","allTopics":["multimodal-learning"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":3,"starsCount":153,"forksCount":10,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-07-02T08:49:05.100Z"}},{"type":"Public","name":"T2I-Adapter","owner":"TencentARC","isFork":false,"description":"T2I-Adapter","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":6,"issueCount":82,"starsCount":3406,"forksCount":200,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-21T20:51:36.081Z"}},{"type":"Public","name":"SmartEdit","owner":"TencentARC","isFork":false,"description":"Official code of SmartEdit [CVPR-2024 Highlight]","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":5,"starsCount":228,"forksCount":6,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-21T11:29:00.928Z"}},{"type":"Public","name":"InstantMesh","owner":"TencentARC","isFork":false,"description":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":94,"starsCount":3055,"forksCount":319,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-20T15:09:04.461Z"}},{"type":"Public","name":"LLaMA-Pro","owner":"TencentARC","isFork":false,"description":"[ACL 2024] Progressive LLaMA with Block Expansion.","allTopics":["llama","llm","llama2"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":23,"starsCount":465,"forksCount":34,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-20T04:51:44.662Z"}},{"type":"Public","name":"Mix-of-Show","owner":"TencentARC","isFork":false,"description":"NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":6,"starsCount":386,"forksCount":17,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-14T04:11:21.479Z"}},{"type":"Public","name":"BTS","owner":"TencentARC","isFork":false,"description":"BTS: A Bi-lingual Benchmark for Text Segmentation in the Wild","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":4,"starsCount":24,"forksCount":0,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-16T07:11:21.708Z"}},{"type":"Public","name":"UMT","owner":"TencentARC","isFork":false,"description":"UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":187,"forksCount":18,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-15T13:20:31.513Z"}},{"type":"Public","name":"BEBR","owner":"TencentARC","isFork":false,"description":"Official code for \"Binary embedding based retrieval at Tencent\"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":42,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-07T05:37:58.157Z"}},{"type":"Public","name":"DeSRA","owner":"TencentARC","isFork":false,"description":"Official codes for DeSRA (ICML 2023)","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":5,"starsCount":123,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-02T12:44:27.484Z"}},{"type":"Public","name":"ViSFT","owner":"TencentARC","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":32,"forksCount":2,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-20T15:44:48.453Z"}},{"type":"Public","name":"MM-RealSR","owner":"TencentARC","isFork":false,"description":"Codes for \"Metric Learning based Interactive Modulation for Real-World Super-Resolution\"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":10,"starsCount":153,"forksCount":12,"license":"BSD 3-Clause \"New\" or \"Revised\" License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-16T09:03:37.704Z"}},{"type":"Public","name":"HOSNeRF","owner":"TencentARC","isFork":false,"description":"HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":2,"starsCount":65,"forksCount":7,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-12T15:35:34.054Z"}},{"type":"Public","name":"VTLayout","owner":"TencentARC","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":1,"starsCount":3,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-10-23T00:21:48.821Z"}},{"type":"Public","name":"TVTS","owner":"TencentARC","isFork":false,"description":"Turning to Video for Transcript Sorting","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":44,"forksCount":2,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-27T18:51:11.343Z"}},{"type":"Public","name":"AnimeSR","owner":"TencentARC","isFork":false,"description":"Codes for \"AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos\"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":8,"starsCount":331,"forksCount":34,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-18T13:09:28.157Z"}},{"type":"Public","name":"pi-Tuning","owner":"TencentARC","isFork":false,"description":"Official code for \"pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation\", ICML 2023.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":32,"forksCount":1,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-21T23:54:55.203Z"}},{"type":"Public","name":"SurfelNeRF","owner":"TencentARC","isFork":false,"description":"SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":4,"starsCount":76,"forksCount":6,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-10T06:30:50.681Z"}},{"type":"Public","name":"GVT","owner":"TencentARC","isFork":false,"description":"Official code for \"What Makes for Good Visual Tokenizers for Large Language Models?\".","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":5,"starsCount":54,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-27T03:44:20.698Z"}}],"repositoryCount":48,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"TencentARC repositories"}