Repositories list

• Alive

  Public

  FoundationVision/Alive’s past year of commit activity
  [Tech Report] Alive: A Unified Audio-Video Generation Model

  3636 forks•503503 stars•66 issues•00 pull requests•Updated Mar 31, 2026Mar 31, 2026

• InfinityStar

  Public

  FoundationVision/InfinityStar’s past year of commit activity
  [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

  generative-modelvideo-generationautoregressive-models+ 1

  generative-modelvideo-generationautoregressive-modelsvisual-generation

  Python

  •

  MIT License

  •2727 forks•747747 stars•88 issues•00 pull requests•Updated Nov 27, 2025Nov 27, 2025

• .github

  Public

  FoundationVision/.github’s past year of commit activity
  00 forks•00 stars•00 issues•00 pull requests•Updated Nov 20, 2025Nov 20, 2025

• UniTok

  Public

  FoundationVision/UniTok’s past year of commit activity
  [NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

  tokenizergenerative-modelimage-generation+ 6

  tokenizergenerative-modelimage-generationgenerativetext-to-imageautoregressive-modelslarge-language-modelsgenerative-aiimage-tokenizer

  Python

  •

  MIT License

  •1111 forks•519519 stars•1616 issues•00 pull requests•Updated Nov 14, 2025Nov 14, 2025

• VAR

  Public

  FoundationVision/VAR’s past year of commit activity
  [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Gen…

  transformersgenerative-modelimage-generation+ 9

  transformersgenerative-modelimage-generationauto-regressive-modelgptneuripsgpt-2diffusion-modelsautoregressive-modelsvision-transformer+ 2

  Jupyter Notebook

  •

  MIT License

  •566566 forks•8.7k8.7k stars•5757 issues•33 pull requests•Updated Nov 10, 2025Nov 10, 2025

• Liquid

  Public

  FoundationVision/Liquid’s past year of commit activity
  (Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators

  generativetext-to-imageimage-gen+ 6

  generativetext-to-imageimage-genautoregressive-modelslarge-language-modelstext-to-image-generationllmsgenerative-aimultimodal-large-language-models

  Python

  •

  MIT License

  •3535 forks•642642 stars•1212 issues•00 pull requests•Updated Nov 10, 2025Nov 10, 2025

• Infinity

  Public

  FoundationVision/Infinity’s past year of commit activity
  [CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

  transformersgenerative-modelimage-generation+ 6

  transformersgenerative-modelimage-generationauto-regressive-modelgpttext-to-imagegpt-2autoregressive-modelstext-to-image-generation

  Python

  •

  MIT License

  •9393 forks•1.6k1.6k stars•6161 issues•55 pull requests•Updated Nov 10, 2025Nov 10, 2025

• Waver

  Public

  FoundationVision/Waver’s past year of commit activity
  Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

  115115 forks•925925 stars•1212 issues•22 pull requests•Updated Aug 27, 2025Aug 27, 2025

• BitVAE

  Public

  FoundationVision/BitVAE’s past year of commit activity
  official training and inference code of bitwise tokenizer

  vaeimage-generationvqvae+ 2

  vaeimage-generationvqvaeautoregressive-modelsimage-tokenizer

  Python

  •

  MIT License

  •22 forks•7171 stars•44 issues•00 pull requests•Updated May 18, 2025May 18, 2025

• GenerateU

  Public

  FoundationVision/GenerateU’s past year of commit activity
  [CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection

  open-worldobject-detectionmultimodality+ 3

  open-worldobject-detectionmultimodalityopen-vocabularymllmopen-vocabulary-detection

  Python

  •

  MIT License

  •88 forks•194194 stars•1515 issues•00 pull requests•Updated Mar 29, 2025Mar 29, 2025

• FlashVideo

  Public

  FoundationVision/FlashVideo’s past year of commit activity
  [AAAI-2026]FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

  generative-modelsvideo-generationdiffusion-models+ 2

  generative-modelsvideo-generationdiffusion-modelstext-to-videoefficient-generative-model

  Python

  •

  Apache License 2.0

  •2626 forks•458458 stars•1313 issues•11 pull request•Updated Mar 5, 2025Mar 5, 2025

• UniRef

  Public

  FoundationVision/UniRef’s past year of commit activity
  [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces

  object-segmentationunified-model

  object-segmentationunified-model

  Python

  •

  MIT License

  •1515 forks•238238 stars•44 issues•00 pull requests•Updated Feb 14, 2025Feb 14, 2025

• flashvideo-page

  Public
  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Feb 10, 2025Feb 10, 2025

• infinity.project

  Public
  HTML

  •00 forks•00 stars•00 issues•00 pull requests•Updated Dec 24, 2024Dec 24, 2024

• GLEE

  Public
  [CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

  trackingopen-worldobject-detection+ 12

  trackingopen-worldobject-detectioninteractive-segmentationvideo-object-segmentationreferring-expression-segmentationreferring-expression-comprehensionvideo-instance-segmentationzero-shot-object-detectionreferring-video-object-segmentation+ 5

  Python

  •

  MIT License

  •7676 forks•1.2k1.2k stars•4545 issues•22 pull requests•Updated Oct 21, 2024Oct 21, 2024

• LlamaGen

  Public

  FoundationVision/LlamaGen’s past year of commit activity
  Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

  image-generationllamaauto-regressive-model+ 4

  image-generationllamaauto-regressive-modeldiffusiontext2imagediffusion-modelsllm

  Python

  •

  MIT License

  •9393 forks•1.9k1.9k stars•7171 issues•11 pull request•Updated Aug 15, 2024Aug 15, 2024

• OmniTokenizer

  Public
  [NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

  vaeimage-generationauto-regressive-model+ 3

  vaeimage-generationauto-regressive-modeltokenizationvideo-generationvqvae

  Python

  •

  MIT License

  •88 forks•323323 stars•99 issues•00 pull requests•Updated Jul 9, 2024Jul 9, 2024

• vaex

  Public
  🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook

  Python

  •

  MIT License

  •88 forks•106106 stars•44 issues•00 pull requests•Updated Jun 23, 2024Jun 23, 2024

• ByteTrack

  Public

  FoundationVision/ByteTrack’s past year of commit activity
  [ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

  real-timedeploymentpytorch+ 1

  real-timedeploymentpytorchmulti-object-tracking

  Python

  •

  MIT License

  •1.1k1.1k forks•6.2k6.2k stars•300300 issues•3030 pull requests•Updated Jun 19, 2024Jun 19, 2024

• Groma

  Public
  [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

  llamamultimodalgrounding+ 6

  llamamultimodalgroundingfoundation-modelslarge-language-modelsllmmllmvision-language-modelllama2

  Python

  •

  Apache License 2.0

  •4545 forks•586586 stars•1616 issues•11 pull request•Updated Jun 7, 2024Jun 7, 2024

• VNext

  Public archive
  Next-generation Video instance recognition framework on top of Detectron2 which supports InstMove (CVPR 2023), SeqFormer(ECCV Oral), and IDOL(ECCV Oral))

  trackingmotiontransformer+ 3

  trackingmotiontransformerobject-detectioninstance-segmentationvideo-instance-segmentation

  Python

  •

  Apache License 2.0

  •5656 forks•616616 stars•4141 issues•11 pull request•Updated Feb 21, 2024Feb 21, 2024