Videosd
TensorRT accelerated diffusion pipeline, combined with webrtc frontend for camera input and speech recognition. Read more…
![](/project/videosd/featured_hu4d9d2330e377e6494cf9d990313c21ec_191754_720x2500_fit_q75_h2_lanczos_3.webp)
TensorRT accelerated diffusion pipeline, combined with webrtc frontend for camera input and speech recognition.
Github repo: https://github.com/venetanji/videosd
See the full video below: