实时互动GPT数字人
- 人体姿态估计和渲染
- 数字人动作与换装换衣试穿.md
- 视频生成.md
- 换脸
- AI换脸系列
- https://github.com/modelscope/facechain.git
- https://github.com/ZHKKKe/MODNet
- AI绘图(stableDiffusion)
- 人脸人体检测分割
- https://github.com/1adrianb/face-alignment
- face-parsing
- DeepLabV3
- https://github.com/PeterL1n/RobustVideoMatting
- AI语音-01-概述
- k2语音识别.md
- whisper
- funasr+Paraformer:https://github.com/modelscope/FunASR
- SenseVoice:https://github.com/FunAudioLLM/SenseVoice
- 角色扮演模型
- Index-1.9B-Character :https://github.com/bilibili/Index-1.9B
- Character-LLM:https://github.com/choosewhatulike/trainable-agents
- 小模型
- miniCPM
- MiniCPM-V
- Phi-3-v
- gemna2b
- tts
- vits,vits2
- bert-vits2学习.md
- gpt-sovits
- fish-speech
- CosyVoice: https://github.com/FunAudioLLM/CosyVoice
- 唱歌tts(singing voice conversion):
- so-vits-svc
- NeuCoSVC
- 聊天tts
- ChatTTS: https://github.com/2noise/ChatTTS
- 其他
- XTTS
- openvoice与MeloTTS
- https://github.com/PaddlePaddle/PaddleSpeech
- 真人数字人项目
- 数字人-01-方案概述
- 虚拟数字人
- 三维重建数字人
- 学习NeRF(新视角合成)
- 3D高斯gaussian-splatting.md
- 苹果联合德国马普所推出的,基于高斯函数的3D数字人合成工具HUGS
- https://machinelearning.apple.com/research/hugs
- 动捕