https://github.com/dvlab-research/jenga
공식 코드Training-Free Efficient Video Generation via Dynamic Token Carving
Papers with Code 아카이브
Video Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 16
- 보존된 평가 기록
- 130
<span style="color:grey; opacity: 0.6">( Various Video Generation Tasks. Gif credit: MaGViT )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dvlab-research/magicmirror
공식 코드Magic Mirror: ID-Preserved Video Generation in Video Diffusion Transformers
https://github.com/eai-lab/on-device-sora
공식 코드On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devices
https://github.com/edenton/svg
공식 코드https://github.com/edouardelasalles/srvp
공식 코드https://github.com/ergastialex/r-flav
공식 코드$^R$FLAV: Rolling Flow matching for infinite Audio Video generation
https://github.com/ewrfcas/uni3c
공식 코드Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
https://github.com/exisas/lgc-vd
공식 코드https://github.com/eyeline-research/survey-video-diffusion
공식 코드Survey of Video Diffusion Models: Foundations, Implementations, and Applications
https://github.com/fabriziogaruti/TabDiT
공식 코드Diffusion Transformers for Tabular Data Time Series Generation
https://github.com/facebookresearch/AnimatedDrawings
공식 코드A Method for Animating Children's Drawings of the Human Figure
https://github.com/facebookresearch/moviegenbench
공식 코드https://github.com/feizc/video-in-context
공식 코드https://github.com/flageval-baai/flagevalmm
공식 코드FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation
https://github.com/fmp453/rectable
공식 코드https://github.com/foundationvision/flashvideo
공식 코드FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
https://github.com/foundationvision/omnitokenizer
공식 코드OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
https://github.com/fuchenustc/videostudio
공식 코드VideoStudio: Generating Consistent-Content and Multi-Scene Videos
https://github.com/fudan-generative-vision/champ
공식 코드Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
https://github.com/fudan-generative-vision/hallo2
공식 코드Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
https://github.com/fudan-zvg/wovogen
공식 코드WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation
https://github.com/g-u-n/animatelcm
공식 코드https://github.com/g-u-n/gen-l-video
공식 코드Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising
https://github.com/gamegen-x/gamegen-x
공식 코드https://github.com/gd-aigc/vmbench
공식 코드VMBench: A Benchmark for Perception-Aligned Video Motion Generation
https://github.com/geekguru123/profilingdit
공식 코드Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models
https://github.com/genforce/StyleSV
공식 코드https://github.com/gigaai-research/general-world-models-survey
공식 코드Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond
https://github.com/google-deepmind/physics-IQ-benchmark
공식 코드https://github.com/google-research/fitvid
공식 코드https://github.com/google-research/google-research/tree/master/infinite_nature
공식 코드Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
https://github.com/google-research/magvit
공식 코드https://github.com/google-research/pix2seq
공식 코드https://github.com/google/storybench
공식 코드StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
https://github.com/gulucaptain/dynamictrl
공식 코드https://github.com/gulucaptain/videoassembler
공식 코드MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.