AI101 - Hands-on
Text
Google translate ,
How It Works
Traditional Natural Language Processing Rosette ,
OnToText ,
Deep Pavlov ,
Epsilon Sys ,
HuggingFace ,
Allen NLP ,
Stanford NLP ,
Explosion.AI - Spacy NER ,
Dandelion NER ,
How It Works
Google Knowledge Graph ,
101 ,
How It Works ,
2
Large Language Models
ChatGPT ,
Perplexity.AI ,
Perplexity.AI Labs Playground ,
Google AI Studio ,
Google NotebookLM ,
Google Gemini ,
Anthropic Claude ,
Bing Chat ,
DeepSeek v3 ,
Lambda Chat ,
Qwen2-72B-Instruct ,
How It Works ,
2 ,
PromptBook
Write With Transformer ,
How It Works ,
2 ,
3 ,
4 (BERT) ,
How It Works
Text to Image
MagicQuill ,
Google Labs - Image-FX ,
Tencent - Flux-Mini ,
Stability.AI ,
Clipdrop - Text to Image ,
PromptHero - Landscape Prompts ,
Freepik ,
Vecteezy ,
Google Gemini ,
Freepik - AI Image Generator ,
Nvidia - Sana ,
How It Works (Annotated) ,
2 ,
List of tools for creating prompts for AI text-to-image generators ,
Image to Image
PhotoMaker ,
PhotoMaker ,
How It Works ,
2
Text to Music Text-to-Music samples with prompts ,
music audio generators ,
Text To Video Runway.ML Gen-2 ,
Haiper ,
Sample Footages ,
How It Works ,
Text to Audio/Image/Video story-telling
Image
Image-2-Text - Moondream (Visual Q&A, Caption, Object Detection)
HuggingFace - SmolVLM-500M
Alibaba Qwen Chat
Image-2-Text - Microsoft Florence 2 (Caption)
Image-2-Text - AllenAI MolMo
VideoLLaMA 3: Frontier Multimodal Foundation Models for Video Understanding ,
Video Understanding
Segment-Anything ,
How It Works ,
2 ,
3
Recognize Anything ,
How It Works
LLaVA: Large Language and Vision Assistant ,
How It Works
Image - Segmentation
Hugging Face Group Face Detection ,
Emotion Recognition ,
ViTPose ,
Image SuperResolution ,
Students studying ,
Image Restoration - How It Works ,
Synthetic Data (to test Fake News Detection algorithms) GAN - This Person Does Not Exist ,
GAN - This X Does Not Exist ,
How It Works ,
2
Single Digit Handwriting
Stable doodle
Google Labs Whisk (not available in SG)
AutoDraw ,
Google Quickdraw ,
How It Works ,
2
Remove Image Background removal.ai ,
remove.bg
Anime GAN
Floorplan (Stanislas Chaillou)
StreetClip
Video (requires WebCam)
PoseNet ,
BodyPix ,
Pose based Video Retrieval ,
How It Works ,
MeshCapade - How It Works
3D PoseNet ,
demo 2 ,
How It Works ,
2
Google Creative Lab - PoseNet
Pose Animator
TREX-2 - Object Counting
Google MediaPipe mediapipe ,
MediaPipe FaceMesh Tracking ,
MediaPipe Hand Tracking ,
HandTrack ,
How It Works ,
2 ,
3 ,
4
mediapipe-for-dummies ,
hand tracking code ,
Audio - Speech / Music
Text-To-Speech
Hume.AI ,
Hume.AI - TikTok Fashion Influencer ,
ElevenLabs ,
Microsoft - EdgeTTS ,
Kokoro-TTS ,
ChatTTS + OpenVoice ,
Play.AI - 2 Speakers ,
FreePik - voice-generator ,
How It Works 1 ,
Speechify ,
Natural Readers ,
How It Works 2
Voice Cloning
llasa-3b-tts ,
CoQui XTTS ,
Sample 1 ,
Sample 2
Text-To-Song
Mureka.AI ,
Music.FX ,
Jammable ,
Suno ,
Tensorflow - Magenta ,
StableAudio,
How It Works
Text-To-Sound Effects
ElevenLabs ,
Yamaha vocaloid
AI Cover Maroon 5: Memories SpongeBob ,
Sun YanZi - Mayday ,
Sun YanZi - Love Story ,
3D
StabilityAI/stable-point-aware-3d (SPAR3D) ,
How It Works
StabilityAI/stable-fast-3d (2D image to 3D)
Tencent - InstantMesh ,
Tencent - Hunyuan3D-2
2D-3D Microsoft TRELLIS
Reading Material
DSTA Medium Page ,
AI Generated Content MindMap
Machine Learning for Everyone
Deep Learning Book
Stanford CS229 - Machine Learning Course
CS231n: Convolutional Neural Networks for Visual Recognition
CV Detailed Guide to Understand and Implement ResNets ,
Start Here with Computer Vision, Deep Learning, and OpenCV
Google Machine Learning Crash Course
Machine Learning Systems Design
Machine Learning Visual Notes
Stanford Speech and Language Processing
Tools and Resources for AI Art
Awesome AI/ML
Yann Lecun ,
Deep Learning Hardware: Past, Present, and Future
Hands-on
Google machine-learning crash-course
100 Days of Machine Learning Coding
AI in the Browser
PYImageSearch - Python & CV
Google AI Experiments
Google TeachableMachine
Knowledge Graph - Mine Information from Text
Fast.AI Practical Deep Learning for Coders , Book
Information Visualization
Image To Image ,
Tensorflow Pix2Pix ,
How It Works
creativitywith.ai
Clipdrop - Stable Diffusion
Stable Diffusion - Cloud-Services
BaseTen ,
RunComfy ,
Replicate ,
RunDiffusion ,
RunPod ,
ThinkDiffusion ,
Stable Diffusion - ComfyUI
OpenArt.AI Templates ,
OpenArt.AI Contest-Winners ,
OpenArt.AI Templates ,
Others
Meta AI demos
Digital Humans HugginFace Sad Talker ,
HeyGen ,
synthesia.io ,
D-ID Chat ,
DeepMotion ,
Leonardo.AI ,
shakker.AI ,
Unreal Metahuman ,
How It Works ,
2 ,
3 ,
LivePortrait ,
LivePortrait Demo 1 ,
LivePortrait Demo 2
prodi.gy named-entity-recognition
ML5js
Oxford - Visual Geometry Group
GAN Lab
Machine Learning Canvas
Artificial Intelligence for Humanitarian Assistance and Disaster Response (HADR) Workshop @ NeurIPS 2019
TensorFlow JS
3D Mapping - Drone Skydio (SketchFab),
Birmingham (SketchFab)
Docubase Tools
2D photo to 3D NeRF in the Wild - Neural Radiance Fields for Unconstrained Photo Collections
MLOps Community
Google Maps 3D ,
2
Google Streeview ,
2
HTML Colors HTML Color Codes
Videos
Re-Work
Two Minute Papers
Datasets
Exploring 12 Million of the 2.3 Billion Images Used to Train Stable Diffusion's Image Generator ,
Exploring the training data behind Stable Diffusion
DataSetList Machine Learning
Google Dataset Search
AMiner Datasets
CV - Event Recognition in Aerial Videos
Benchmarking Measuring the Progress of AI Research ,
Github ,
Chatbot Arena ,
Artificial Analysis ,
Synthetic Data MakeSense.AI (label photos)
Microsoft Designer (sign-in with Microsoft account)
Sample Sounds Google AudioSet ,
FreeSound ,
LAION Audio Dataset Project ,
VGG-Sound ,
AudioCaps ,
WavCaps ,
Sample Text Chinese News - ZaoBao
Sample Video FreePik - People ,
FreePik - Nature ,
PictoGraphic ,
UnSplash ,
PixaBay ,
Pexels ,
StockSnap.io ,
PicJumbo ,
Flickr ,
Adobe Stock Collection ,
Shopify Burst ,
Sample Videos for PoseNet
Dance Videos for PoseNet 1 ,
Dance Videos for PoseNet 2 ,
BTS Fire ,
GD X TAEYANG 'Good Boy' mirrored Dance Practice ,
Meghan Trainor - NO / Learner's Class ,
Maroon 5 - Memories / Woomin Jang Choreography for PoseNet 3
|