Skywork

All

34 repositories

UniPic
Public
Unified Multimodal Model for image generation/editing/understanding
image image-editing image-generation vlm understanding diffusion-models aigc qwen-image
Python
•
MIT License
•33•785•21•0•Updated Sep 8, 2025Sep 8, 2025
Matrix-3D
Public
Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.
graphics genie 3d-reconstruction 3d-generation video-generation image-to-video world-models scene-generation text-to-video image-to-3d
Python
•
MIT License
•35•491•21•0•Updated Sep 2, 2025Sep 2, 2025
Matrix-Game
Public
Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
real-time genie video-generation interactive-video long-sequence world-model long-video
Python
•
MIT License
•162•1.6k•15•0•Updated Aug 21, 2025Aug 21, 2025
Skywork-DeepResearch
Public
0•23•1•0•Updated Aug 13, 2025Aug 13, 2025
DeepResearchAgent
Public
DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.
gaia multiagent-systems general-purpose multimodel
JavaScript
•
MIT License
•340•2.5k•4•4•Updated Aug 13, 2025Aug 13, 2025
SkyReels-V2
Public
SkyReels-V2: Infinite-length Film Generative model
Python
•
Other
•582•4.5k•47•5•Updated Aug 11, 2025Aug 11, 2025
skyreels-a3.github.io
Public
project for skyreels-a3
JavaScript
•4•69•0•0•Updated Aug 9, 2025Aug 9, 2025
MindLink
Public
Python
•
Apache License 2.0
•7•96•16•0•Updated Aug 8, 2025Aug 8, 2025
Skywork-R1V
Public
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI (Kunlun Inc.), specializing in vision-language reasoning.
reinforcement-learning reasoning vlm llm multimodal-understanding deepseek-r1 grpo vlm-r1 multimodal-r1 r1v
Python
•
MIT License
•270•2.9k•26•0•Updated Aug 2, 2025Aug 2, 2025
Skywork-Reward-V2
Public
Scaling Preference Data Curation via Human-AI Synergy
1•107•8•0•Updated Jul 3, 2025Jul 3, 2025
CSVQA
Public
A Multimodal Benchmark for Evaluating Scientific Reasoning Capabilities of VLMs
benchmark reasoning mllm mllm-evaluation mllm-reasoning
Python
•
Apache License 2.0
•0•6•0•0•Updated Jun 6, 2025Jun 6, 2025
Skywork-OR1
Public
Unleashing the Power of Reinforcement Learning for Math and Code Reasoners
Python
•
Apache License 2.0
•44•714•17•0•Updated Jun 6, 2025Jun 6, 2025
SkyReels-A1
Public
SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers
condition-render portrait-animation video-diffusion-transformers
Python
•
Other
•60•560•15•1•Updated Jun 5, 2025Jun 5, 2025
skyreels-audio.github.io
Public
JavaScript
•0•5•0•0•Updated Jun 3, 2025Jun 3, 2025
SkyReels-A2
Public
SkyReels-A2: Compose anything in video diffusion transformers
controllable-generation image2video video-diffusion-transformers
Python
•
Other
•62•672•24•2•Updated Jun 3, 2025Jun 3, 2025
Mureka-mcp
Public
generate lyrics, song and background music(instrumental). Model Context Protocol (MCP) server.
Python
•
MIT License
•8•55•0•1•Updated May 13, 2025May 13, 2025
skyreels-a1.github.io
Public
JavaScript
•0•4•0•0•Updated Apr 10, 2025Apr 10, 2025
skyreels-a2.github.io
Public
JavaScript
•0•2•0•0•Updated Apr 9, 2025Apr 9, 2025
SkyReels-V1
Public
SkyReels V1: The first and most advanced open-source human-centric video foundation model
t2v i2v video-diffusion-transformers
Python
•
Other
•255•2.3k•51•5•Updated Mar 10, 2025Mar 10, 2025
Skywork
Public
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc.
llm
Python
•
Other
•136•1.4k•14•1•Updated Mar 7, 2025Mar 7, 2025
SuperCorrect-llm
Public
Python
•3•4•0•0•Updated Dec 30, 2024Dec 30, 2024
MVGamba
Public
[NeurIPS2024] MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
Python
•3•63•2•0•Updated Dec 11, 2024Dec 11, 2024
agent-studio
Public
Environments, tools, and benchmarks for general computer agents
Python
•
GNU Affero General Public License v3.0
•24•12•0•0•Updated Dec 3, 2024Dec 3, 2024
skywork-o1-prm-inference
Public
Python
•
Apache License 2.0
•5•65•5•1•Updated Nov 26, 2024Nov 26, 2024
MoH
Public
MoH: Multi-Head Attention as Mixture-of-Head Attention
transformer moe attention vit dit mixture-of-experts llms
Python
•
Apache License 2.0
•14•274•4•0•Updated Oct 29, 2024Oct 29, 2024
Vitron
Public
NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
segmentation mllm multimodal-large-language-models
Python
•35•567•15•0•Updated Oct 20, 2024Oct 20, 2024
MoE-plus-plus
Public
[ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts
moe mixture-of-experts large-language-models llms
Python
•
Apache License 2.0
•11•239•1•2•Updated Oct 16, 2024Oct 16, 2024
Skywork-Reward
Public
Skywork Reward Model Series
1•11•1•1•Updated Sep 6, 2024Sep 6, 2024
DAQ-VS
Public
Code For Our Work: DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries [ECCV-2024]
0•14•0•0•Updated Jul 11, 2024Jul 11, 2024
LLMs-as-Instructors
Public
Python
•1•4•0•0•Updated Jul 2, 2024Jul 2, 2024