Large Language Models15 min read
How Image Generation Actually Works
The real process behind Midjourney, Gemini, FLUX, and ChatGPT
ReadTopic
Generative AI
Generative AI is not one thing. Images, video, audio, text, and code all have different constraints. This page groups the articles that explain those mechanisms in plain English.
generativegenerationgeneratediffusionimage generationvideo generationaudiomusicdallstable
AI Agents23 min read
How to Clean Up AI-Generated Drafts Without Sounding Like ChatGPT
How to Spot and Remove “AI Slop” from Your Writing
Read
AI Engineering10 min read
Open-Sora 2.0 Explained: Architecture, Training, and Why It Matters
How Open-Sora 2.0 Built Sora-Level Video AI for $200K
Read
Large Language Models14 min read
Inside ChatGPT: How AI Understands and Generates Language
How ChatGPT Actually Works - no math, no code
Read
Large Language Models3 min read
From Zero to LLM Hero: Announcing Our Python Primer for Generative AI
The Python Primer the Industry Needs is Here
Read
Large Language Models10 min read
Optimizing RAG: Should you Fine-Tune?
Optimizing Large Language Models for Retrieval-Augmented Generation
Read
Large Language Models6 min read
Long Context Models Explained: Do We Still Need RAG?
Retrieval-Augmented Generation vs. Long Context: A Comprehensive Comparison
Read
RAG and Retrieval9 min read
How to Effectively Evaluate Retrieval-Augmented Generation (RAG) Systems
Why RAG Evaluation Matters and Techniques to Leverage
Read
Large Language Models6 min read
Top RAG Techniques You Should Know (Wang et al., 2024)
Building the Best RAG Stack: A Breakdown of Wang et al.'s Goldmine Study
Read
Generative AI8 min read
The Hidden Dangers of AI in Coding: What You Need to Know
Coding with Generative AI: Benefits, Risks, and Practical Solutions
Read
Computer Vision8 min read
The Future of Video Generation: Deep Dive into Stable Video Diffusion
Stable Video Diffusion Explained
Read
Generative AI7 min read
Understanding Distil-Whisper: A Closer Look at AI's Role in Audio Transcription
Distil-Whisper: AI's New Approach to Efficient Audio Transcription
Read
Computer Vision58 min read
Revolutionizing AI Applications: Dmitry Shapiro's Vision for MindStudio
This is an interview with Dmitry Shapiro, previously working at Google and CTO of MySpace Music. Now, Dmitry is building something super ambitious with the goal of democratizing ar
Read
Large Language Models7 min read
Meet Our new AI Tutor!
How we Built an Open-Source RAG-based ChatGPT Web App
Read
Computer Vision7 min read
DALLE 3 Explained: Improving Image Generation with Better Captions
OpenAI’s BEST text-to-image model to date!
Read
Computer Vision6 min read
Generate music with AI: Stable Audio Explained
New AI That Generates Amazing Music !
Read
Computer Vision7 min read
StyleGANEX: Enhancing Image Manipulation with Dilated Convolutions
Enhance Your Photos with AI: From HD Upscaling to Cartoon Filters
Read
Computer Vision9 min read
Revolutionizing Online Shopping: AI's Virtual Try-On Experience
AI Does magic with UNets, Diffusion, and clothes!
Read
RAG and Retrieval6 min read
Image Manipulation with Your Mouse! Drag Your Gan Explained
Move anything from point A to point B!
Read
Large Language Models1 min read
Copilot, ChatGPT and Copyrights
An interview with David Mertz, senior developer, data scientist, and author
Read
Large Language Models5 min read
Your Dictionary for AI in 2023
Logan Kilpatrick's Definitions for all the words to know for OpenAI, GPT and AI in 2023
Read
Large Language Models2 min read
An Interview with OpenAI's Developer Advocate Logan Kilpatrick
Building with LLMs, ChatGPT, and Working at OpenAI With Logan Kilpatrick (Dev Rel @OpenAI) - What's AI episode 11
Read
Computer Vision5 min read
Perfusion: Stable Diffusion but more Controllable!
The new Perfusion model by NVIDIA Explained
Read
Computer Vision6 min read
Gen-1, the future of storytelling?
Turn mockups into videos automatically!
Read
Generative AI1 min read
What's it like to work in Generative AI?
An interview with the VP of R&D at a Generative AI company (D-ID)
Read
Computer Vision6 min read
From Audio to Talking Heads in Real-Time with AI! RAD-NeRF explained
Efficient NeRFs for Real-Time Portrait Synthesis (RAD-NeRF)
Read
Computer Vision5 min read
InfiniteNature-Zero: Fly Into Your Pictures With AI!
Generate infinite new frames as if you would be flying into your image!
Read
Computer Vision6 min read
eDiffi explained: New SOTA Image Synthesis model!
NVIDIA's new model has better results, more control and more fidelity than DALLE and Stable Diffusion!
Read
Computer Vision6 min read
Diffusion models: Everything you need to know
Here's every vision application Diffusion models were a game changer in 2022: image, text, video, 3D, and more!
Read
Computer Vision7 min read
AI Image Editing from Text! Imagic Explained
Imagic: Manipulate images using pre-trained image generator models!
Read
Computer Vision5 min read
3D Models from Text! DreamFusion Explained
How AI generates 3d models from only text!
Read
Computer Vision5 min read
Guiding Stable Diffusion with your Images
Personalizing Text-to-Image Generation using Textual Inversion
Read
Generative AI7 min read
One of the Most Challenging Tasks for AI
A New Challenging Task for AI: panoptic scene graph generation
Read
AI Engineering5 min read
How Stable Diffusion works? Latent Diffusion Models Explained
A High-Resolution Image Synthesis Architecture: Latent Diffusion
Read
Computer Vision6 min read
Produce Amazing Artworks with Text and Sketches!
"Make-A-Scene": a fantastic blend between text and sketch-conditioned image generation.
Read
Generative AI5 min read
CVPR 2022 Best Paper Honorable Mention: Dual-Shutter Optical Vibration Sensing
They reconstruct sound using cameras and a laser beam on any vibrating surface, allowing them to isolate music instruments, focus on a specific speaker, remove ambient noises, and many more amazing applications.
Read
Computer Vision4 min read
How does dalle-mini work?
Dalle mini is a free, open-source AI that produces amazing images from text inputs. Here's how it works.
Read
Computer Vision6 min read
Google Brain's Answer to Dalle-e 2: Imagen
An AI that creates photorealistic images from input text better than Dall-e 2!
Read
Computer Vision5 min read
This is a BIG step for GANs! BlobGAN Explained
A GAN model that uses simple blobs to manipulate objects in images…
Read
Computer Vision7 min read
OpenAI's new model DALL·E 2 is amazing!
An amazing new model by OpenAI capable of generating and inpainting images from a text input with incredible results!
Read
Computer Vision7 min read
Impressive photo restoration by AI !
This new and completely free AI model can fix most of your old pictures in a split second!
Read
Generative AI6 min read
Speech Inpainting with AI !
Grammar, Pronunciation & Background Noise Correction with AI !
Read
Computer Vision8 min read
Create Realistic 3D Renderings with AI !
From a few images to a 3D model using AI!
Read
Large Language Models6 min read
New SOTA Image Captioning: ClipCap
Easily generate text descriptions for images using CLIP and GPT models!
Read
Computer Vision5 min read
CityNeRF: 3D Modelling at City Scale!
Generate city-scale 3D scenes with high-quality details at any scale!
Read
Computer Vision8 min read
NVIDIA EditGAN: Image Editing with Full Control From Sketches
Control any feature from quick drafts, and it will only edit what you want keeping the rest of the image the same! SOTA Image Editing from sketches model by NVIDIA, MIT, UofT.
Read
Generative AI7 min read
Text-to-Drawing Synthesis With Artistic Control | CLIPDraw & StyleCLIPDraw
Take a picture of the style you want to copy, enter the text, and the algorithm will generate a new picture out of it!
Read
Generative AI9 min read
Isolate Voice, Music, and Sound Effects With AI
If we take an audio clip with the music way too loud, you can simply turn up the speech and lower the music!
Read
Generative AI6 min read
Generate Video Variations - No dataset or deep learning required!
This model can do any video manipulation or video generation application you have in mind!
Read
Generative AI7 min read
How to Make Slow Motion Videos With AI!
TimeLens can understand the movement of the particles in-between the frames of a video to reconstruct what really happened at a speed even our eyes cannot see. In fact, it achieves results that our intelligent phones and no other models could reach before.
Read
Computer Vision7 min read
Manipulate Real Images With Text - An AI For Creative Artists! StyleCLIP Explained
AI could generate images, then, using a lot of brainpower and trial and error, researchers could control the results following specific styles. Now, you can do that using only text!
Read
Computer Vision7 min read
Make GANs Training Easier for Everyone : Generate Images Following a Sketch
Control GANs outputs based on the simplest type of knowledge you could provide it: hand-drawn sketches.
Read
AI Engineering7 min read
Image Synthesis and Editing from Sketches: SDEdit. No more tedious training needed!
Say goodbye to complex GAN and transformer architectures for image generation. This new method can generate new images from any user-based inputs.
Read
Computer Vision7 min read
How Apple Photos Recognizes People in Private Photos Using Machine Learning
Using multiple machine learning-based algorithms running privately on your device, Apple allows you to accurately curate and organize your images and videos on iOS 15.
Read
Computer Vision6 min read
OpenAI's New Code Generator: GitHub Copilot (and Codex)
Find out how this AI Generates Code From Words
Read
Computer Vision4 min read
⏩ How AI Generates New Images: GANs Put Simply
Understand how AI creates new images using Generative Adversarial Networks in 2 minutes
Read
AI Engineering8 min read
CVPR 2021 Best Paper Award: GIRAFFE - Controllable Image Generation
Using a modified GAN architecture, they can move objects in the image without affecting the background or the other objects!
Read
Computer Vision8 min read
Barbershop: Try Different Hairstyles and Hair Colors from Pictures (GANs)
This AI can transfer your hair to see how it would look like before committing to the change.
Read
Generative AI10 min read
How to Spot a Deep Fake. Breakthrough US Army technology (2021)
How to Spot a Deep Fake in 2021. Breakthrough US Army technology using artificial intelligence to find deepfakes.
Read
Computer Vision6 min read
Articulated 3D Reconstruction from Videos
Generate 3D models of humans or animals moving from only a short video as input.
Read
Computer Vision6 min read
Infinite Nature: Fly into an image and explore the landscape
The next step for view synthesis: Perpetual View Generation, where the goal is to take an image to fly into it and explore the landscape!
Read
Computer Vision8 min read
Create 3D Models from Images! GANverse3D & NVIDIA Omniverse
This promising model called GANverse3D only needs an image to create a 3D figure that can be customized and animated!
Read
Computer Vision5 min read
OpenAI’s DALL·E: Text-to-Image Generation Explained
OpenAI just released the paper explaining how DALL-E works! It is called “Zero-Shot Text-to-Image Generation”.
Read
Computer Vision6 min read
Train Your GAN With 1/10th of the Data! NVIDIA ADA Explained
With this new training method developed by NVIDIA, you can train a powerful generative model with one-tenth of the images! Making possible many applications that do not have access to so many images!
Read