KlingTeam/PixelMoE
Updated • 1
AI & ML interests
The Kling Team is building next-generation multimodal world models across video, audio, text, 3D, and beyond. We are continuously looking for exceptional talent to join us. Feel free to reach out!
Recent Activity
View all activity
Papers
Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling
Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers
KlingTeam/ShotStream
Text-to-Video • Updated • 20
KlingTeam/TimePLE
Image-Text-to-Text • 9B • Updated • 106 • 4
KlingTeam/StreamHOI
Updated • 3
KlingTeam/UnityVideo
Text-to-Video • Updated • 184 • 9
KlingTeam/DecMem
Video-to-Video • Updated • 8
KlingTeam/X-Dub
Updated • 26
KlingTeam/CamCloneMaster-Wan2.1
Updated • 16
KlingTeam/VANS
Updated • 6
KlingTeam/MultiShotMaster
Updated • 14
KlingTeam/UniVideo
Any-to-Any • Updated • 104
KlingTeam/MemFlow
Text-to-Video • Updated • 13
KlingTeam/StereoPilot
Video-to-Video • Updated • 20
KlingTeam/SVG-T2I
Text-to-Image • Updated • 35 • 35
KlingTeam/VidEmo-7B
Video-Text-to-Text • 8B • Updated • 36 • 6
KlingTeam/VidEmo-3B
Video-Text-to-Text • 4B • Updated • 31 • 7
KlingTeam/StyleMaster
Updated • 4
KlingTeam/VFRTok
Other • Updated • 3
KlingTeam/HumanAesExpert-8B
8B • Updated • 132 • 8
KlingTeam/HumanAesExpert-1B
0.9B • Updated • 177 • 6
KlingTeam/MODA
Updated • 1
KlingTeam/RoboMaster
Updated • 4
KlingTeam/SynCamMaster-Wan2.1
Updated • 4
KlingTeam/ReCamMaster-Wan2.1
Updated • 23
KlingTeam/LivePortrait
Image-to-Video • Updated • 20.8k • 519
KlingTeam/VideoReward
Updated • 30
KlingTeam/3DTrajMaster
Updated • 7