FoundationVision

All

21 repositories

Alive
Public
17•299•6•0•Updated Feb 15, 2026Feb 15, 2026
InfinityStar
Public
[NeurIPS 2025 Oral]Infinity⭐️: Uniﬁed Spacetime AutoRegressive Modeling for Visual Generation
generative-model video-generation autoregressive-models visual-generation
Python
•
MIT License
•26•720•14•0•Updated Nov 27, 2025Nov 27, 2025
.github
Public
0•0•0•0•Updated Nov 20, 2025Nov 20, 2025
UniTok
Public
[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding
tokenizer generative-model image-generation generative text-to-image autoregressive-models large-language-models generative-ai image-tokenizer
Python
•
MIT License
•11•510•15•0•Updated Nov 14, 2025Nov 14, 2025
VAR
Public
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Gen…
transformers generative-model image-generation auto-regressive-model gpt neurips gpt-2 diffusion-models autoregressive-models vision-transformer
Jupyter Notebook
•
MIT License
•560•8.6k•55•3•Updated Nov 10, 2025Nov 10, 2025
Liquid
Public
(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators
generative text-to-image image-gen autoregressive-models large-language-models text-to-image-generation llms generative-ai multimodal-large-language-models
Python
•
MIT License
•34•637•12•0•Updated Nov 10, 2025Nov 10, 2025
Infinity
Public
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
transformers generative-model image-generation auto-regressive-model gpt text-to-image gpt-2 autoregressive-models text-to-image-generation
Python
•
MIT License
•85•1.5k•61•4•Updated Nov 10, 2025Nov 10, 2025
Waver
Public
Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.
108•892•11•2•Updated Aug 27, 2025Aug 27, 2025
BitVAE
Public
official training and inference code of bitwise tokenizer
vae image-generation vqvae autoregressive-models image-tokenizer
Python
•
MIT License
•2•69•3•0•Updated May 18, 2025May 18, 2025
GenerateU
Public
[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection
open-world object-detection multimodality open-vocabulary mllm open-vocabulary-detection
Python
•
MIT License
•8•191•15•0•Updated Mar 29, 2025Mar 29, 2025
FlashVideo
Public
[AAAI-2026]FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
generative-models video-generation diffusion-models text-to-video efficient-generative-model
Python
•
Apache License 2.0
•25•457•13•1•Updated Mar 5, 2025Mar 5, 2025
UniRef
Public
[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces
object-segmentation unified-model
Python
•
MIT License
•15•236•4•0•Updated Feb 14, 2025Feb 14, 2025
flashvideo-page
Public
HTML
•0•0•0•0•Updated Feb 10, 2025Feb 10, 2025
infinity.project
Public
HTML
•0•0•0•0•Updated Dec 24, 2024Dec 24, 2024
GLEE
Public
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
tracking open-world object-detection interactive-segmentation video-object-segmentation referring-expression-segmentation referring-expression-comprehension video-instance-segmentation zero-shot-object-detection referring-video-object-segmentation
Python
•
MIT License
•76•1.2k•45•2•Updated Oct 21, 2024Oct 21, 2024
LlamaGen
Public
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
image-generation llama auto-regressive-model diffusion text2image diffusion-models llm
Python
•
MIT License
•94•1.9k•67•1•Updated Aug 15, 2024Aug 15, 2024
OmniTokenizer
Public
[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
vae image-generation auto-regressive-model tokenization video-generation vqvae
Python
•
MIT License
•8•322•9•0•Updated Jul 9, 2024Jul 9, 2024
vaex
Public
🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook
Python
•
MIT License
•8•105•4•0•Updated Jun 23, 2024Jun 23, 2024
ByteTrack
Public
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
real-time deployment pytorch multi-object-tracking
Python
•
MIT License
•1.1k•6.1k•299•30•Updated Jun 19, 2024Jun 19, 2024
Groma
Public
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
llama multimodal grounding foundation-models large-language-models llm mllm vision-language-model llama2
Python
•
Apache License 2.0
•45•582•16•1•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))
tracking motion transformer object-detection instance-segmentation video-instance-segmentation
Python
•
Apache License 2.0
•55•618•41•1•Updated Feb 21, 2024Feb 21, 2024