AI Agent Skills

✨ Reverse-engineered Python API for Google Gemini web app

Image-to-Image Translation in PyTorch

AI film director skills for Claude agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1, Nano Ba…

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3,…

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Image-to-image translation with conditional adversarial nets

[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, i…

Seedance 2.0 prompt skill，使用该Skill生成Seedance 2.0 视频提示词

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity