Tencent's Open-Source WeMM-Embedding Runs Video Retrieval on an RTX 3060
huangyun_122 · x · 2026-09-13
A user tested Tencent's open-source WeMM-Embedding model, using it to pull out all shots and clips showing computer desktops from a Three-Body video—and it ran stably on their RTX 3060. The author says the model enables many video-derived applications and asks for more ideas.
More from Multimodal
- 10-Person Startup Phonic Claims #1 on Five Speech Benchmarks With Phonic-1 — graceisford · 2026-10-31
- Halloween doorway: Midjourney prompt builds a giant moth crossing a star-forest cliff — tisch_eins · 2026-10-31
- Open-source ComfyUI Motion Previs Studio brings 3D camera blocking to AI video — navarisun · 2026-10-31
- Open-Source ComfyUI Motion Previs Studio Blocks 3D Shots Before Video Generation — navarisun · 2026-10-31
- Hooking Mage's MCP into Claude generated narrative image sets in one shot — AIandDesign · 2026-10-31
- At 3 am she stops scrolling and a whole town answers in songs — AI short film — ownubie · 2026-10-31