zhangnn520 / my_sadtalker

Related projects ⓘ

Alternatives and complementary repositories for my_sadtalker

• zvxme / wav2lip_chinese
  ☆70Updated last month
• langzizhixin / wav2lip-576x576
  This is a project about talking faces. We use 576X576 sized facial images for training, which can generate 2k, 4k, 6k, and 8k digital hum…
  ☆49Updated 8 months ago
• langzizhixin / lil
  ☆53Updated last year
• monk-after-90s / wav2lip_data_preprocess
  wav2lip训练数据预处理综合工具
  ☆37Updated last year
• langzizhixin / Double_Talker
  ☆50Updated last year
• zhangbo2008 / wav2lip384_my2
  ☆38Updated 10 months ago
• chengyuanba / avatar_ernerf
  Just a suturing monster project.
  ☆37Updated last year
• nghiakvnvsd / wav2lip_data_preprocessing
  ☆32Updated last year
• zhenhehhhhh / Insightface-wav2lip
  ☆27Updated last year
• instant-high / wav2lip-onnx-256
  Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation
  ☆27Updated last month
• rogerle / wav2lip_train
  ☆31Updated last year
• langzizhixin / IP_LAP_GFPGAN
  ☆30Updated 10 months ago
• foxyear-kyumin / lip_mask
  通过此代码可以免训练模型并通过轻量级服务器定制数字人形象
  ☆99Updated 7 months ago
• zzj1111 / Preprocessed-CMLR-Dataset-For-Wav2Lip
  Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…
  ☆59Updated last year
• langzizhixin / Wav2Lip-CodeFormer
  ☆193Updated last year
• Aruen24 / wav2lip_288x288_test
  ☆46Updated last year
• monk-after-90s / wav2lip_288x288
  ☆10Updated last year
• nghiakvnvsd / wav2lip384
  ☆190Updated 10 months ago
• AIFSH / NativeDancer
  make your charactor Dancing as Native style
  ☆41Updated 11 months ago
• numz / wav2lip_uhq
  Wav2Lip UHQ Improvement with ControlNet 1.1
  ☆73Updated last year
• hhhwmws0117 / GLM-VITS-SadTalker
  浅尝LLM
  ☆33Updated last year
• wanggang1987 / fast_sadtalker
  ☆12Updated last year
• Spycsh / xtalker
  Faster Talking Face Animation on Xeon CPU
  ☆120Updated last year
• oneCodeSuperman / wav2lip_hq_trt
  这是一个在wav2lip，使用wav2lip、gfpgan、yolov5等模型用RT加速的超快推理！经测试在2070显卡上可达到0.03秒每帧实现实时推理。
  ☆26Updated last year
• instant-high / wav2lip-onnx
  simple and fast wav2lip using onnx models for face-detection and inference. Easy installation
  ☆22Updated last month
• notiom / ER-nerf
  主要写er-nerf从零到一所有部署过程
  ☆37Updated 2 months ago
• ShineChen1024 / MiaoBi
  Chinese Stable Diffusion, zh SD,中文文生图，中文SD，中文Stable Diffusion
  ☆44Updated 8 months ago