Picsart AI Research (PAIR)

All

15 repositories

StreamingT2V
Public
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
long-video-generation
Python
•153•1.5k•38•0•Updated Dec 2, 2024Dec 2, 2024
MI-GAN
Public
[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices
knowledge-distillation image-inpainting object-removal re-parameterization mobile-inpainting mi-gan
Python
•
MIT License
•46•504•8•1•Updated Nov 12, 2024Nov 12, 2024
OpenBias
Public
[CVPR 2024 Highlight] OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
Python
•2•19•1•0•Updated Jul 9, 2024Jul 9, 2024
Zero-Painter
Public
🔥 [CVPR 2024] The official repo for Zero-Painter!
computer-vision generative-ai cvpr2024 zero-painter
Python
•
MIT License
•4•64•3•0•Updated Jun 8, 2024Jun 8, 2024
PAIR-Diffusion
Public
[CVPR 2024] PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor
Python
•
MIT License
•22•508•7•0•Updated Apr 2, 2024Apr 2, 2024
Social-Reward
Public
Python
•0•9•1•0•Updated Mar 29, 2024Mar 29, 2024
HD-Painter
Public
HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models
Python
•
MIT License
•17•300•14•0•Updated Mar 14, 2024Mar 14, 2024
LIVE-Layerwise-Image-Vectorization
Public
[CVPR 2022 Oral] Towards Layer-wise Image Vectorization
image-vectorization
Python
•
Apache License 2.0
•54•504•5•0•Updated Feb 26, 2024Feb 26, 2024
Specialist-Diffusion
Public
[CVPR 2023] Specialist Diffusion: Extremely Low-Shot Fine-Tuning of Large Diffusion Models
Python
•3•35•3•0•Updated Oct 17, 2023Oct 17, 2023
SeMask-Segmentation
Public
[NIVT Workshop @ ICCV 2023] SeMask: Semantically Masked Transformers for Semantic Segmentation
pytorch semantic-segmentation cityscapes ade20k vision-transformers coco-stuff-10k semask
Python
•
Other
•36•252•7•0•Updated Oct 9, 2023Oct 9, 2023
IPL-Zero-Shot-Generative-Model-Adaptation
Public
[CVPR 2023] Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
Python
•
MIT License
•9•83•5•0•Updated Aug 3, 2023Aug 3, 2023
Text2Video-Zero
Public
[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators
video-editing video-generation
Python
•
Other
•354•4.1k•45•3•Updated May 6, 2023May 6, 2023
ReCoRo-Controllable-Low-Light-Image-Enhancement
Public
[ACMMM 2022] ReCoRo: Region-Controllable Robust Light Enhancement by User-Specified Imprecise Masks
image-processing image-restoration low-level-vision low-light-image-enhancement
Python
•2•14•2•0•Updated Feb 6, 2023Feb 6, 2023
Mask-Matching-Transformer
Public
Python
•3•13•3•0•Updated Jan 12, 2023Jan 12, 2023
VideoINR-Continuous-Space-Time-Super-Resolution
Public
[CVPR 2022] VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
Python
•27•277•8•0•Updated Oct 9, 2022Oct 9, 2022