stepfun-ai
stepfun-ai's tracked open-source repos, sorted by stars.
- #1★ 3,188+2Star change over the last 7 days
- #2
STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.
★ 2,260+4Star change over the last 7 days - #3
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
★ 2,257+3Star change over the last 7 days - #4
Fast, Sharp & Reliable Agentic Intelligence
★ 2,072+1Star change over the last 7 days - #5
Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.
★ 1,507+4Star change over the last 7 days - #6
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech
★ 971+0Star change over the last 7 days - #7
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
★ 885+1Star change over the last 7 days - #8★ 697+0Star change over the last 7 days
- #9
[🚀 ICLR 2026 Oral] NextStep-1: SOTA Autogressive Image Generation with Continuous Tokens. A research project developed by the StepFun’s Multimodal Intelligence team.
★ 696+0Star change over the last 7 days - #10
A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.
★ 586+1Star change over the last 7 days - #11
Step-DeepResearch
★ 571-1Star change over the last 7 days
