暂未收录效果图
查看技能说明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…
OPENAGENTSKILL / DIRECTORY
为下一项任务找到合适的技能。探索适用于 Codex、Claude Code、Cursor 等 Agent 的工具。
6 Skills
搜索结果: 6
暂未收录效果图
查看技能说明HorizonWind2004
[ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models…
暂未收录效果图
查看技能说明readbeyond
aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
暂未收录效果图
查看技能说明echogarden-project
Cross-platform speech toolset, used from the command-line or as a Node.js library. Includes a variety of engines for speech synthesis, speech recognition, forced alignme…
暂未收录效果图
查看技能说明gudaochangsheng
[ECCV 2026] Official PyTorch implementation of RefAlign: Representation Alignment for Reference-to-Video Generation
暂未收录效果图
查看技能说明Phantom-video
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
暂未收录效果图
查看技能说明gooseworks-ai
Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated cha…