Tencent Releases CoinVE-200K Dataset and 22B Video Editing Model
tencent · hf · 2026-08-19
Tencent introduced CoinVE-200K, a large-scale, high-quality dataset for compositional instruction-guided video editing. The release includes a new benchmark and a 22B parameter model, enabling complex editing tasks via multi-region attention and temporal coherence.
More from Multimodal
- AI Short Film Made for $90 vs. Millions for Studios — sirajraval · 2026-08-19
- Asked GPT for an ugly house, got a wildly cool structure — Aizkmusic · 2026-08-19
- New Platform Launch: Create and Showcase AI-Generated 3D Models — anselm · 2026-08-19
- Create "Big-Head 3D Cartoon" Knitted-Style Characters with AI — aziz4ai · 2026-08-19
- Fully local MiniMax H3 prompt enhancement: a ComfyUI workflow guide — Patient_Ratio4177 · 2026-08-19
- Midjourney prompt for long-exposure pinhole camera effect — tisch_eins · 2026-08-19