Wildminder (@wildmindai)
2025-12-30 | โค๏ธ 270 | ๐ 32
Stream-DiffVSR: A low-latency, streamable video super-resolution model;
- distills Stable Diffusion Upscaler to just 4 steps;
- processes 720p ~3fps. https://jamichss.github.io/stream-diffvsr-project-page/ https://x.com/wildmindai/status/2005930126505304378/video/1
๐ ์๋ณธ ๋งํฌ
- https://jamichss.github.io/stream-diffvsr-project-page/
- https://x.com/wildmindai/status/2005930126505304378/video/1
๋ฏธ๋์ด
๐ Related
- what-if-you-could-make-a-robots-ai-brain-more-stable-and
- video-models-serve-as-a-good-pretrained-backbone-for-robot
- what-if-we-could-train-ai-robots-in-a-perfect-physics
- twist2-scalable-portable-and-holistic-humanoid-data
- large-video-planner-enables-generalizable-robot-control