360 AI Research

All

13 repositories

WISA
Public
World Simulator Assistant for Physics-Aware Text-to-Video Generation
Python
•
Apache License 2.0
•4•33•2•0•Updated May 16, 2025May 16, 2025
FG-CLIP
Public
New generation of CLIP with fine grained discrimination capability, ICML2025
clip fine-grained-classification cross-modal-retrieval text-image-retrieval
Python
•3•92•3•0•Updated May 14, 2025May 14, 2025
FancyVideo
Public
Video generation from text&image, 1st-gen
video-generation image-to-video text-to-video
Python
•51•923•18•0•Updated May 10, 2025May 10, 2025
Qihoo-T2X
Public
Efficient DiT architecture for text2any tasks, ICLR2025
image-generation efficient-dit
22•448•2•0•Updated May 10, 2025May 10, 2025
RelaCtrl
Public
Efficient controlnet for DiTs
image-generation controlled-generation controlnet efficient-dit
Python
•34•296•22•0•Updated May 10, 2025May 10, 2025
.github
Public
Introduction to 360 AI Research
Apache License 2.0
•0•0•0•0•Updated Apr 23, 2025Apr 23, 2025
Inner-Adaptor-Architecture
Public
LMM solved catastrophic forgetting, AAAI2025
lmm large-multimodal-models
Python
•
Apache License 2.0
•4•43•1•0•Updated Apr 15, 2025Apr 15, 2025
PlanGen
Public
Unified layout planning and image generation
image-generation grounding controlled-generation layout-control
Python
•
Apache License 2.0
•0•17•2•0•Updated Apr 14, 2025Apr 14, 2025
HiCo_T2I
Public
Layout Conditioned Image Generation, NeurIPS2024
image-generation layout-control neurips-2024
Python
•3•57•11•0•Updated Mar 31, 2025Mar 31, 2025
Bridge_Diffusion_Model
Public
Chinese-native image generation while compatible with SD eco-system, 1st-gen, AAAI2025
text-to-image latent-diffusion stable-diffusion chinese-native
Python
•
Apache License 2.0
•1•12•3•0•Updated Jun 25, 2024Jun 25, 2024
360VL
Public
Our 2nd-gen LMM
Python
•
Apache License 2.0
•2•33•4•0•Updated May 22, 2024May 22, 2024
SEEChat
Public
Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM
chatbot gpt4 mllm
Python
•
Apache License 2.0
•9•100•2•0•Updated May 17, 2024May 17, 2024
OVD_Contest
Public
Public page for open vocabulary detection contest 2023
objectdetection ovd multimodal openset-classification crossmodal
MIT License
•3•6•6•0•Updated Jan 9, 2024Jan 9, 2024