AI142 Segment Anything Inpaint https://www.youtube.com/watch?v=ORWDULfmk40 Segment Anything 을 이용해서 inpaint할때 쉽게 선택하는 방법을 알려드릴게요! * colab 사이트 주소 https://github.com/ninjaneural/webui * 프롬프트 정보 https://github.com/ninjaneural/webui/blob/master/memo/segmentany.md [로컬PC 사용자] * Segment Anything 익스텐션 *원본* https://github.com/continue-revolution/sd-webui-segment-anything *영상에 설명한 기능추가 버전* https://github.com/ninjaneural/sd-webui-segment.. 2023. 5. 13. 영상만들기, 특정부위만 교체 https://www.youtube.com/watch?v=MVE-10PbHE4 https://www.youtube.com/watch?v=5TWbSpxmyRAhttps://www.youtube.com/watch?v=Tj1LfskLZh0 https://www.youtube.com/watch?v=5TWbSpxmyRA 2023. 5. 2. Whisper JAX Whisper JAX - up to 70x faster than OpenAI Whisper Whisper를 그래픽 가속을 했더니 70배 빨라졌다고 합니다. https://github.com/sanchit-gandhi/whisper-jax GitHub - sanchit-gandhi/whisper-jax Contribute to sanchit-gandhi/whisper-jax development by creating an account on GitHub. github.com https://github.com/openai/whisper/discussions/1277 2023. 5. 1. TTS 글자를 음성으로 생성해주는데 효과음등과 주변음 등도 생성해주는 모델이 나왔습니다. https://tango-web.github.io/ Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model Deepanway Ghosal1, Navonil Majumder1, Ambuj Mehrish1, Soujanya Poria1 1DeCLaRe Lab, Singapore University of Technology and Design, Singapore Abstract The immense scale of the recent large language models (LLM) allows many interesting propertie.. 2023. 5. 1. 이전 1 ··· 19 20 21 22 23 24 25 ··· 36 다음
