LIHQ
AvatarGAN
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
LIHQ
- Seeking Open Source Tools for Lifelike Digital Avatar and TTS with Multilingual Support
-
What models are digital avatars like Synthesia using ?
project: https://github.com/johnGettings/LIHQ
- 100% AI including verse, photo, outpainting, animation, voice, and lip syncing
-
If the CTE turned Bapa into a good person
ElevenLabs + Wav2lip can create something similar to this. There's also this
-
Looking for help with an idea for my fiance on our wedding day
Option 1) I built something that will do the exact thing you're looking for. It requires approximately 30 seconds of the person's voice (clean, isolated) and a high quality image of them looking straight into the camera. Not sure if you can get either of those. It's completely free and you don't need any fancy hardware but you need to build it out yourself. I'll say now that it's not as good as what you'll find from a big name tech company but it's the best free option you'll find online. https://github.com/johnGettings/LIHQ
- Turn a photo into a talking head by uploading audio?
-
Replika meets Artbreeder meets D-ID Creative Reality™️
If anyone wants to try something similar but for free, you could use LIHQ, it uses an uploaded photo and has a voice replicator or general TTS. Though it uses google colab and takes some getting used to.
-
I Created an Automated Finance News Channel with Python and AI
You might enjoy this repo I created, if you want to add an AI human to the video. Check out the demo video. https://github.com/johnGettings/LIHQ
-
Introducing LIHQ - High Quality Artificial Speaker (Open source in google colab)
Link to the GitHub: https://github.com/johnGettings/LIHQ
AvatarGAN
-
What will you do with your MtgoxNFT?
Could start with a GAN produced cartoon collection. https://github.com/aakashjhawar/AvatarGAN
What are some alternatives?
gan-vae-pretrained-pytorch - Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.
Deep-Learning - In-depth tutorials on deep learning. The first one is about image colorization using GANs (Generative Adversarial Nets).
GAN-Anime-Characters - Applied several Generative Adversarial Networks (GAN) techniques such as: DCGAN, WGAN and StyleGAN to generate Anime Faces and Handwritten Digits.
RefinementGAN - Official implementation of the paper: https://arxiv.org/abs/2108.04957
Transformer-in-Transformer - An Implementation of Transformer in Transformer in TensorFlow for image classification, attention inside local patches
nn - 🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
faceswap-GAN - A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
pillbox - Contains implementation of AdVIL, AdRIL, and DAeQuIL algorithms from the ICML '21 Paper Of Moments and Matching.