Alibaba’s EMO: Emotional portraits come alive
EMO, a framework capable of generating emotion-filled portrait videos based…
ChatMusician: A large language model capable of understanding and generating music
By using conditions such as given text prompts, chord sequences,…
MeloTTS: A high-quality multilingual text-to-speech (TTS) library developed by MyShell AI
Supports multiple languages such as English, Spanish, French, Chinese, Japanese…
STORM: An innovative writing system
Challenge: Wikipedia-style articles require in-depth research and planning, including extensive…
Introduction to Chrome’s good extensions
1. ScribeHow / @ScribeHow 2. GoFullPage 3. Color Zilla 4….
OpenAI has a place to experience Sora’s features in advance
OpenAI’s technical report There is a place to experience Sora’s…
SDXL Lightning real-time picture generation
Generating pictures while typing, the speed is extremely fast
There have been some changes to the ChatGPT codebase
Some content related to English language/translation files, image generation style…
StabilityAI launches image enhancement tool: Creative Upscaler
Resolution improvement: Upgrade the image to 4K resolution, regardless of…
YOLOv9: Real-time object detection that quickly and accurately identifies and locates multiple objects in an image or video
Compared with previous YOLO series models, YOLOv9 achieves lightweight models…