360 AI Research

360 AI Research's repositories

FancyVideo

Video generation from text&image, 1st-gen

Language:Python921 43 24

Qihoo-T2X

Efficient DiT architecture for text2any tasks, ICLR2025

450 32 2

FG-CLIP

New generation of CLIP with fine grained discrimination capability, ICML2025

Language:PythonApache-2.0430 2 33

RelaCtrl

Efficient controlnet for DiTs

Language:Python381 26 22

WISA

World Simulator Assistant for Physics-Aware Text-to-Video Generation

Language:PythonApache-2.0247 28 11

SEEChat

Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM

Language:PythonApache-2.0101 2 6

HiCo_T2I

Layout Conditioned Image Generation, NeurIPS2024

Language:Python64 1 12

LMM-Det

Make Large Multimodal Models excel in object detection, ICCV 2025

Language:PythonApache-2.051 3 2

Inner-Adaptor-Architecture

LMM solved catastrophic forgetting, AAAI2025

Language:PythonApache-2.04403

360VL

Our 2nd-gen LMM

Language:PythonApache-2.03405

PlanGen

Unified layout planning and image generation, ICCV2025

Language:PythonApache-2.031 2 5

MiniCPM-o.cpp

Inference of MiniCPM-o 2.6 in plain C/C++

Language:C++Apache-2.023 10

Bridge_Diffusion_Model

Chinese-native image generation while compatible with SD eco-system, 1st-gen, AAAI2025

Language:PythonApache-2.01304

OVD_Contest

Public page for open vocabulary detection contest 2023

MIT6019

.github

Introduction to 360 AI Research

Apache-2.0000

llama.cpp

LLM inference in C/C++

Language:C++MIT000