#video-generation Repositories
288 repositories total
A Minimalist, Batteries-included Repository for Advancing World Model Science.
[ICML 2024] MagicPose (also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
Vibe Knowledge Showcase: One knowledge point โ one polished knowledge short with voiceover and a source for every sentence (Claude Code skill ยท 44 style sets ยท code turns it into a finished video frame by frame)
AdCraft โ The first agentic video production platform for marketing and advertising. Infinite canvas ยท shot-by-shot replication ยท fully automatedโfrom idea to final cut.
[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
SparkDiffusion: Accelerating DiT video generation by 265ร via joint sparsity, distillation, quantization, etc.
Multi-agent AI pipeline that turns one line of text into a finished short-form drama: script, cinematic storyboards, character-consistent video. Provider-agnostic (OpenAI/Claude, MJ, Minimax, Veo/Sora, fal, ComfyUI). MIT.
A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, and Enthusiasts.
[ICCV 2025] Official implementation of the paper โMagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Controlโ
[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
Reverse-engineers prompts from AI videos, features audio analysis to extract video dialogues and scripts, and allows you to edit the video you want with just a single sentence.
On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
Tools, ComfyUI workflows and benchmark configs from a 4x RTX 3090 local-inference rig
[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"
[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC
A shadcn registry of Remotion components for product demo videos. Install a text reveal, device frame, terminal session, logo sting, or an entire scene with a command.
[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Short-Form Drama Workbench | MiniMax H3 Workflow for Videos of Unlimited Length | ComfyUI Plugin for Local Short-Form Drama and Long-Video Generation
Bilingual (Chinese + English) ML / LLM / diffusion / agent interview cheat sheets for AI autumn recruiting โ generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML that can be read anywhere โ plus a CVโDBLP fact-checked academic homepage generator and hand-authored long-form blogs ๐ฑ
Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP โ storyboard, references, generation, editable first cut on a real timeline. Local-first: projects, prompts, and keys stay on your machine. No account, no telemetry.
[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
[SIGGRAPH ASIA 2024 TCS] AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds.
Free, open-source alternative to Weavy AI, Krea Nodes, Freepik Spaces & FloraFauna AI โ node-based AI workflow builder for generative image & video pipelines
Refine and improve the quality of small faces in MiniMax H3 videos. Track faces frame by frame, crop them, refine them with H3, and stitch them back in.
[CVPR 2025, TPAMI 2026] UniScene: Unified Occupancy-centric Driving Scene Generation
GPT Image 2 to Seedance 2.5 Early Access workflow guide.
Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)
[ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling
[ICLR 2026] Streamlining Cartoon Production with Generative Post-Keyframing