10 Commits
Author SHA1 Message Date
hay86 d13b0e70c1 Merge branch 'main' of https://github.com/fudan-generative-vision/hallo into fudan-generative-vision-main 2024-07-15 09:37:40 +00:00
xumingw 83dd4ebf52 fix: bug #124 (#133)
add temp unet in log validation
add face emb validation in extract meta info function
2024-07-04 11:21:08 +08:00
xumingw 53bc81aed7 feat: data preprocessing code of hallo (#103)
* feat: data preprocessing code of hallo

* add data preprocessing
* add utils functions of data preprocessing
* add image processor and audio processor of data preprocessing

* fix: train config and data processing param adjustment

* add model weight postprocess after stage1
* make data processing param easier to understand
2024-06-27 14:54:01 +08:00
xumingw 0152cd969e feat: training code of hallo (#101)
* add training code and corresponding config yaml files
* add some auxiliary funciton in utils
* fix a parameter bug in motion module
* fix mask size issue in stage2 dataset module "talk_video.py"
2024-06-27 00:54:16 +08:00
hay86 638cb1673e comfyui node done 2024-06-26 06:13:59 +00:00
AricGammaandleeway.zlw c92a25e5dd feat: merge config with cli args (#89)
Co-authored-by: leeway.zlw <leeway.zlw@outlook.com>
2024-06-25 00:04:40 +08:00
crystallee 25f032f4a2 fix: add audio padding only in FaceAnimatePipeline (#74) 2024-06-22 17:30:34 +08:00
AricGammaandleeway.zlw d8e2ccc833 fix: optimize gradio demo. remove unnecessary options (#76)
Co-authored-by: leeway.zlw <leeway.zlw@outlook.com>
2024-06-21 13:08:47 +08:00
cocktailpeanut 07ffd49627 feat: gradio WebUI (#51)
* WebUI + Audio Fix

1. audio fix: explicitly specify the audio codec in `util.py`, otherwise the video is technically corrupt and doesn't play sound
2. web ui: gradio web ui
3. print the current step while running inference

gradio

* lint

* update
2024-06-20 14:01:24 +08:00
crystallee 6a3e6e355b feat: base inference code of hallo (#1)
* feat:base inference code of hallo

* fix:remove debug code
2024-06-15 02:22:03 +08:00