Stars
VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)
Universal and Transferable Attacks on Aligned Language Models
[ACL 2025 Oral] 🔥🔥 MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval
Explore the Multimodal “Aha Moment” on 2B Model
Xposed虚拟摄像头，适用于Android9.0+; Xposed virtual camera, available for Android 9.0+
Building DeepSeek R1 from Scratch
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
Generative Models by Stability AI
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
期刊分区查询小工具，包括中科院分区表升级版（2025、2023、2022）及国际期刊预警名单（2025、2024、2023、2021、2020）、JCR（2023、2022、2021、2020）、CCF推荐国际会议和期刊目录（2022）、计算领域高质量科技期刊分级目录（2022）。
Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"
Open-Sora: Democratizing Efficient Video Production for All
[AAAI 2024] "LDMVFI: Video Frame Interpolation with Latent Diffusion Models", Duolikun Danier, Fan Zhang, David Bull
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL
[TMLR 2025] Latte: Latent Diffusion Transformer for Video Generation.
MagicEdit: High-Fidelity Temporally Coherent Video Editing
[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
LLaMA: Open and Efficient Foundation Language Models
[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.
Finetune ModelScope's Text To Video model using Diffusers 🧨
Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability
A curated list of recent diffusion models for video generation, editing, and various other applications.