Hey everyone!
Today, I’ve got some exciting updates for you from the world of generative AI.
Facepoke
Facepoke is super easy to use and lets you control any part of a still image with just a few clicks. You can try it out for free using the demo version, but keep in mind, if many people are using it at the same time or if you’re far from the hosting servers, you might experience some delay. https://huggingface.co/spaces/jbilcke-hf/FacePoke
https://github.com/jbilcke-hf/FacePoke?tab=readme-ov-file
XDoG Sketch
This web app turns your pictures into artistic sketches! It uses a method called XDoG, which enhances the edges of your images and gives them a cool, sketchy look. Perfect for adding some artistic flair to your photos.
Check it out here: XDoG Sketch on GitHub
bolt.new
This is a new feature from StackBlitz called “Bolt.” It helps you create things like Twitter threads, presentations, or animated videos right in your browser. No complicated setup needed—just fast, easy, and powerful.
Try it here: bolt.new
Scenario
Scenario is an AI tool designed to help businesses plan for the future. It uses data to predict different situations and helps you choose the best strategy. They recently added a feature called “MULTI-LoRA,” which lets you adjust models in real-time while you work on specific sections.
Check out Scenario: Scenario AI
Blinkshot
Blinkshot is a platform that generates images in real time using Flux Schnell. The best part? It’s free and doesn’t even require registration. It’s a fast and easy way to create images with AI.
Try Blinkshot here: Blinkshot
EdgeRunner
NVIDIA’s EdgeRunner is an AI model that creates 3D models. It’s great at making high-quality 3D meshes without the usual problems like incomplete parts or lack of detail. Now, it can create more complex and realistic 3D shapes.
Learn more here: NVIDIA EdgeRunner
3D Doll ControlNet
This AI model helps you control the poses and expressions of 3D characters using text commands. The results look like 3D models, but they might not be entirely realistic. Still, it’s a cool tool for 3D character control.
Find it here: 3D Doll ControlNet on Hugging Face
DepthFlow
DepthFlow is a tool that adds depth and movement to your images, making them look like they’re popping out of the screen. You can easily turn your images into depth-based videos with this customizable parallax shader.
Check it out here: DepthFlow on GitHub
Voice-Pro
Voice-Pro is a software that combines subtitling, translation, and text-to-speech in one package. It supports over 100 languages and 400 different voices, making it a great tool for creating subtitles and voiceovers in multiple languages.
Explore Voice-Pro: Voice-Pro on GitHub
Depth Pro and Depth Flow Workflow
These workflows can be used in ComfyUI to enhance your images with depth effects. They are great for creating videos with a 2.5D effect, adding more dimension to your static images.
Check out the workflow here:
DepthFlow Workflow
FaceFusion
FaceFusion is a powerful face-swapping framework. It can be tricky to install, but once it’s set up, it does an impressive job swapping faces in photos and videos.
Get started with FaceFusion: FaceFusion on GitHub
TorchChat
TorchChat now supports all Llama 3.2 models, including vision models! It allows you to run large language models on your desktop, server, or even mobile devices, making it super flexible for various applications.
Learn more here: TorchChat on GitHub
That’s all for today’s updates! See you next time for more AI news.