Another digital human / digital avatar test, this time using a LORA trained Wan2.1 model on 27 images.
(I've used ComfyUI for inference/tests. This is WIP: just 14 epochs trained)
#wan21 #machinelearning #diffusion #comfyui #avatar
George Profenza
@orgicus
- First tests trying out Gaussian Avatars ! Congratulations to the teams at @TU_Muenchen and @Woven_Toyota for the amazing work ! project: shenhanqian.github.io/gaussian-avata… paper: arxiv.org/abs/2312.02069 code: github.com/ShenhanQian/Ga… #avatar #gaussiansplatting #machinelearning
- @drv_kmr has been working hard on his first Kickstarter campaign: a beautiful programmable light piece. Its controllable via #dmx (#streamingacn #artnet) as well as #mqtt Home Automation. It uses temp, CO2, humidity sensors driving Tamagotchi like interactions with simulated fishLivegrid is published on @Hacksterio with a heavy headline🙃. We need more exposure like this, please share Livegrid in your network and help us reach the right people. 25 days to go ! kickstarter.com/projects/liveg… #IoT #digitalart #environmentalawareness #homeassistant #opensource
- I'm fortunate to be giving a talk on the @opencvlibrary Webinar today to talk about Invisible: the Markerless Motion Capture solution by @disguise_one and move.ai. It will not to technical,but hopefully fun Feel free to join me in a few hours: 9AM PDT / 5PM GMTThis Thursday on OpenCV Live we'll get a visit from OpenCV community member George Profenza, who will be showing us the new hotness in motion capture: It's called "Invisible"
- I've been fortunate enough to make it to the @ChiliPeppers concert this weekend. The solos from @johnfrusciante were blissful. This is my nerdy #mathart tribute using @GnuOctave
