DeepFaceLab
DISCONTINUED
avatarify
Our great sponsors
DeepFaceLab | avatarify | |
---|---|---|
91 | 21 | |
43,236 | 16,075 | |
- | - | |
4.4 | 4.6 | |
5 months ago | 27 days ago | |
Python | Python | |
GNU General Public License v3.0 only | GNU General Public License v3.0 or later |
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.
DeepFaceLab
-
DeepFaceLab VS facefusion - a user suggested alternative
2 projects | 30 Jan 2024
- Civitai founder champions open source, downplays AI deepfake porn (article on venturebeat)
-
roop-unleashed
AFAIK the only app which supports whole head swapping is DeepfaceLab but it needs to be trained with lots of images and lacks a proper GUI.
-
List of AI-Models
Click to Learn more...
- [Deepfakessfw] Meilleur moyen de créer un deepfake pour vidéos avec un logiciel gratuit pour le créer
- This Morgan Freeman deepfake
-
From single photo to Dreambooth model
This could be a good departure point too as well: https://github.com/iperov/DeepFaceLab
-
I compared TheLastBen's Fast DreamBooth with my "Improved" DreamBooth training - you be the judge!
At the moment it's still part of DeepFaceLab (https://github.com/iperov/DeepFaceLab) but I'm planning on removing unneeded dependencies and on releasing it as a "standalone" for DreamBooth usage..
-
What’s the best way to get started in deep fake video as a complete noob with a Mac and plenty of programming experience (but not anything media or numerical)?
If you mean face swaps, then DeepFaceLab is probably still the best, https://github.com/iperov/DeepFaceLab My rig is a potato so I use the google colab, https://github.com/chervonij/DFL-Colab
-
AMA (Emad here hello)
The waves around this and the personal responsibility discussion are interesting, for example https://github.com/iperov/DeepFaceLab is still around after many years.
avatarify
-
Voice changing app
Face changer. On windows deepFaceLive and (GNU/linux, windows) avatarify.
-
vee pee enn
The other method which is common on short videos like tiktok or imgur is an app called Avatarify. All those zoom pranks were done with this app. It is different than Deepfacelab as you are letting the GPU map your face and apply an image over it. its more instantaneous, but not necessarily worse in quality. This is how you see paintings move or those weird "video killed the radio star" sing alongs.
-
[P] I used neural networks to enhance and animate Isaac Newton from an old painting.
I saw avatarify some time ago and the underlying model is also first order
-
Anyone has link for code to this? Just to label some old photos and animate (still a beginner, dunno if you can animate or teach TF to do facial expressions)
MyHeritage uses "Deep Nostalgia" to do theirs, but it might be based on this Samsung AI (https://bigthink.com/technology-innovation/new-ai-can-create-fake-videos-of-people-from-a-single-picture) or maybe this git (https://github.com/alievk/avatarify)
There's also this which allows you to use a webcam and a source such as the mona lisa and use the output with Zoom, skype etc. https://github.com/alievk/avatarify
-
[N] AI can turn old photos into moving Images / Link is given in the comments - You can also turn your old photo like this
git haven’t tried it yet tho
Idk what software OP is using, but there is this https://github.com/alievk/avatarify.
-
Le Deep Fake c'est fun. (je suis tellement désolée)
Franchement la réalisation est bien faite, j'imagine le boulot que ça demande pour le montage après. J'avais déjà testé cette solution de deep fake ainsi que celle d'avatarify en mode visio (https://github.com/alievk/avatarify) qui utilise le même model.
What are some alternatives?
faceswap - Deepfakes Software For All
DeepFaceLive - Real-time face swap for PC streaming or video calls
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
Deep-Fakes
fast-stable-diffusion - fast-stable-diffusion + DreamBooth
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
DFL-Colab - DeepFaceLab fork which provides IPython Notebook to use DFL with Google Colab
FaceFusion - Next generation face swapper and enhancer
PaddleGAN - PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
GFPGAN - GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
figaro - Real-time voice-changer for voice-chat, etc. Will support many different voice-filters and features in the future. 🎵
yanderifier - First-Order-Wrapper (formerly known as Yanderify) is a front-end tool for first-order-motion. It aims to make using first-order-motion face animation accessible to everyone, for education and entertainment.