Jianzhu Guo
Jianzhu Guo
Thanks @jsntcheng ! How about the execution time (latency) of `match_histograms`?
Hi @NielsRogge , the weights of LivePortrait have already been released on [HuggingFace](https://huggingface.co/KwaiVGI/LivePortrait/tree/main). Let us know if there's anything else we should provide!
Merged. Greak thanks! > Thanks! I've opened a PR to add a pipeline tag https://huggingface.co/KwaiVGI/LivePortrait/discussions/37, feel free to merge
The code and models of LivePortrait are under MIT license. The code of InsightFace is under MIT licenser, but the models of InsightFace are not. For commercial usage, you should...
And welcome to recommend other licensed, fast, and effective face detection models.
The license is updated. @macztk
Thanks for your feedback. @chrsbats Can MediaPipe run on GPU?
@jfischoff But LivePortrait use InsightFace's 106 landmarks model to detect the landmarks as the initial ones (although LivePortrait provides a 203 landmarks model with ONNX format). From what I know,...
Not support now @tivikoff . You can forcely use the stitching and retargeting modules from humans, but it may lead to worse results.
In theory, the GPU memory should not overflow, as LivePortrait currently performs inference frame by frame. One situation that can occur is when the driving video is too long, causing...