#video-generation Repositories
288 repositories total
A curated list of papers on reinforcement learning for video generation
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
[CVPR'25] Official Implementations for Paper - AniDoc: Animation Creation Made Easier
Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation
[arXiv 2026] WorldCrafter: Consistent Video World Model with Implicit 3D-Aware Memory
Async Python wrapper for Seedance, Kling, MiniMax and Wan video generation. Supports CLI and a local web UI
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Improved AnimateAnyone implementation that allows you to use the opse image sequence and reference image to generate stylized video
AI video factory: from one topic to a finished, multilingual YouTube video. Claude agents write, plan, draw, and review; a Studio keeps the human in charge.
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable SparseโLinear Attention
[arxiv'26] GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
AI skill collection for faceless video channels: investigative long-form videos and hand-drawn whiteboard explainers. Turn a topic into a complete video in one promptโwith voice-over, subtitles, thumbnail, and copy tailored to each platform.
Genblaze is an open source Python SDK for orchestrating generative AI media pipelines across video, audio, and image providers with built in provenance for every output.
Multi-model DAG-driven parallel AI film generation โ parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "Transform the execution graph of audiovisual generation from topological order to critical path optimal scheduling"; The only film generation engine that models scene narrative dependencies as DAG and drives parallel scheduling with CPM algorithm
[ICCV 2025] Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Frametell: Turn your ideas and materials into vivid explainer videos with an AI director agent. Local-first, any model.
[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving
Claude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change, beat-synced SFX, 60 fps motion blur. v2: use with Claude Opus 5.5.
A set of ComfyUI nodes providing additional control for the LTX Video model
Python wrapper for ByteDance's Seedance 2.5 and Seedance 2.5 Flash API, with Spicy relaxed-moderation routes for uncensored-style video generation, text/image-to-video, native 4K, and MCP via MuAPI.
[ICLR 2025] Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
[ICLR 2024 Spotlight] Official implementation of ScaleCrafter for higher-resolution visual generation at inference time.
[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation
Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.
OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions (NeurIPS 2025)