Video & audio
No visual example yet
Explore the skill
Lance
bytedance
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
1,2 rbGitHub
Lihat skill0Unduhan situs
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Temukan skill untuk tugas berikutnya dengan Codex, Claude Code, Cursor, dan lainnya.
Hasil · “unified”
3 Skills
Hasil: 3
Unduhan situs
File yang dikirim situs ini sejak 14 Oktober 2026. Satu hitungan per akun masuk, Skill, dan hari UTC. Tidak termasuk situs luar, salinan perintah, atau instalasi. Pembaruan hingga 5 menit.
Video & audio
No visual example yet
Explore the skillBernini
bytedance
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
836GitHub
Lihat skill0Unduhan situs
Video & audio
No visual example yet
Explore the skill
Reconstruction Alignment
HorizonWind2004
[ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models…
406GitHub
Lihat skill0Unduhan situs
Panduan & perbandingan
- Frontend design skills ↗
- Remotion skills ↗
- Excel and XLSX skills ↗
- PDF and Word skills ↗
- AI agent skills library ↗
- Open source AI agent skills ↗
- Best Codex skills ↗
- Best AI agent skills for stock analysis ↗
- Best Codex skills for web scraping ↗
- Best Claude Code skills for PDF parsing ↗
- Best AI agent skills for football analytics ↗
- OpenAgentSkill vs skills.sh ↗
- OpenAgentSkill vs agentskills.io ↗