johndpope/Emote-hack
Emote Portrait Alive - using ai to reverse engineer code from white paper. (abandoned)
Python
Issues
- 0
- 0
- 0
- 6
I found some bugs and questions.
#30 opened by wangshiwen-ai - 0
An alternative project EchoMimic is open-sourced
#36 opened by lymhust - 20
take a look at this
#31 opened by fenghe12 - 2
Our approach incorporates the last n frames, termed ’motion frames’ - currently stuck on this.
#27 opened by johndpope - 3
Hi，how is the progress？
#33 opened by jeffreyking23 - 1
VASA-1 hack
#34 opened by johndpope - 1
- 1
AnimateAnyone
#32 opened by wangshiwen-ai - 1
backbone network == diffused heads backbone
#29 opened by johndpope - 0
AudioLayers and AudioFeatureModel
#19 opened by johndpope - 0
- 0
- 0
It's just me (and ai) against Alibaba
#26 opened by johndpope - 2
Referencenet input/output shape
#24 opened by sarperkilic - 1
freezing the FramesEncoderVAE - claudeai
#25 opened by johndpope - 1
check this out
#22 opened by Inferencer - 2
Where is the reference net config??
#21 opened by murphytju - 3
- 1
TODO - replace resnet with retinaface
#6 opened by johndpope - 0
Got any thoughts on the paper Vs code - use this https://docs.google.com/spreadsheets/d/1meRHgcFZ8mxWplvJweAd-5P_tkH0UeD2eT2Ot_k46jA/edit#gid=865829673
#11 opened by johndpope - 1
how to train this demo，thanks！
#20 opened by fenghe12 - 2
Looks similar to DINet
#15 opened by Inferencer - 1
Thanks and Status Update
#14 opened by fire17 - 1
Data url not avaiable
#12 opened by cuishuhao - 4
1.5 billion image data questions
#10 opened by CHK-0000 - 4
Data Preparation:
#1 opened by johndpope - 2
FaceLocator
#8 opened by johndpope - 1
Unit Testing:
#3 opened by johndpope - 6
Implement the model architecture:
#2 opened by johndpope - 2
Implement 3 Training Stages
#4 opened by johndpope - 2
Decord + cuda12
#9 opened by johndpope - 2
Implment Face Region + Face Locator
#5 opened by johndpope - 1
Create Speed Encoder
#7 opened by johndpope