DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions, which is developed by the Department of Electronic Engineering at Tsinghua University and ByteDance.

Some interesting transcription model wrapper

Lemon8 wrapper in Python

【Star us and watch this project grow! 🌱⭐️】Collection of algorithm problems and solutions from ByteDance MarsCode Youth Training Camp (Winter 2024-2025). This repository contains coding challenges and their implementations used in the camp's entrance assessment.

A ComfyUI custom node for ByteDance's Seedream 4 image generation model via the Replicate API. Generate high-quality images with advanced control over aspect ratios, multi-image generation, and seed management.

Cog wrapper for SeedVR2 (3B/7B) video & image restoration with optional color fix

🎭Cogified HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning🗣️

🎥 Generate human-centric videos through collaborative multi-modal conditioning with HuMo, enhancing video content creation and interaction.

The examples of my work

实时语音对话程序，支持语音输入和语音输出，基于火山引擎端到端大模型