google-ai-edge / mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

Home Page:https://ai.google.dev/edge/mediapipe

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Support for additional plugins for Image Generation task

jyorien opened this issue · comments

Have I written custom code (as opposed to using a stock example script provided in MediaPipe)

No

OS Platform and Distribution

Android

MediaPipe Tasks SDK version

No response

Task name (e.g. Image classification, Gesture recognition etc.)

Image Generation

Programming Language and version (e.g. C++, Python, Java)

Java

Describe the actual behavior

This task only supports Edge, Face and Depth for condition images

Describe the expected behaviour

Be able to use my own plugin types, apart from Edge, Face, and Depth Map

Standalone code/steps you may have used to try to get what you need

NA

Other info / Complete Logs

Is there any way to use other plugins besides the provided ones, such as openpose, as my condition image type, or would I have to rewrite a custom pipeline or edit the existing pipeline from the C++ graph in this repo?

Hi @jyorien,

Please allow us some time to discuss this with the team. Once we have received their input, I will provide you with any updates.

Thank you!!