GAM segmentação da Meta

GAM Colab + tensorflow

Colab how-to-segment-anything-with-sam.ipynb

GAN

ChatGPT is not all you need. A State of the Art Review of large Generative AI models

• Google Doc A cat sitting in a chair, wearing a pair of sunglasses

• DALL·E 2 and AI art prompt resources & tools to inspire beautiful images

• photomaker or IP adapter

• demo de chat gpt

• Voice -> text -> chatgpt -> text -> voice

• brain Awesome ChatGPT Prompts

• Let's build GPT: from scratch, in code, spelled out Video plus Colab

Hugging Face Transformers Examples

matrix multiplications alpha tensor

text and question from a image to text

separar audio

pixelart

image to story

tag 2 text

[object detection](https://huggingface.co/spaces/ShilongLiu/Grounding_DINO_demo]

Segment Anything Model (SAM): a new AI model from Meta AI that can "cut out" any object, in any image, with a single click

Difusao Video + Text Command

Text to Audio

Editando Images com comandos em texto and colab

Image Similarity with Hugging Face Datasets and Transformers

TorchYolo: YOLO Series Object Detection and Track Algorithm Library

Object Detection with KerasCV

how to use Keras and Diffusion

Have you ever imagined what a corgi-alike coffee machine or a tiger-alike rabbit would look like?

code generator

Creating visualizations for presentations sucks.

Generate article from few words

Dream Studio

InstructPix2Pix Learning to Follow Image Editing Instructions

• introducao ao Gradio

• Gradio demo for VideoMAE for video classification. To use it, simply upload your video or click one of the examples to load them. Read more at the links below.

• Question and Answer

• Yolo v6 Video

• Anime

• Clustering and Sklearn

• Vision-and-Language Transformer (ViLT), fine-tuned on VQAv2

• Extremely-Fast diffusion text-to-speech synthesis pipeline with ProDiff and FastDiff

• Classification and Sklearn

• How do you draw an owl: 1. draw some circles 2. click "Diffuse the rest"

• Week 1 Project: Building a Leaf Classification App

• Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation

• Semantic Segmentation with MobileViT and DeepLabV3

• Unsupervised Salient Object Detection with Spectral Cluster Voting

• {CVPR conference click on HF space](https://huggingface.co/spaces/CVPR/CVPR2022_papers)

• Dall-e mini text to images

• Demo list

• Github gradio

• Generate mandarin speech from text

• Text generation complete...

• Small Object Detection with SAHI + YOLOv5

• Vit - Bamboo for Image Recognition Demo (https://github.com/Davidzhangyuanhan/Bamboo).

• Gradio Blocks examples

  • Introduction to Blocks
  • Pypi Dynamic Plots
  • Several Demos

Yolo demo in Website

Minerva - wo hundred undergraduate-level problems in physics, biology, chemistry, economics, and other sciences that require quantitative reasoning, and find that the model can correctly answer nearly a third of them.

colab introduction

Free GPT3

Keras tutorial Text generation

Recent Deep Learning Links + explanations

Text Abstract to Title

Image Generation

Imagen unprecedented photorealism × deep level of language understanding + github&paper

• thispersondoesnotexist
• thispizzadoesnotexist
• thishorsedoesnotexist
• Psychedelics in a Fantasy Land

• Image Captioning with VirTex model trained on RedCaps
• DALL·E: Creating Images from Text
• Merge art Dall-e
• CLIP: Connecting Text and Images
• Chrome extension to read a paper + video
• Image to text DEMO
• Awesome Text-to-Image - A collection of resources on text-to-image synthesis task.

• Knowledge Transfer in Self Supervised Learning

• Ted How AI could compose a personalized soundtrack to your life | Pierre Barreau
• Bardo Composer
• I am AI - Aiva
• Plutonium - Rock Song Composed by AI | AIVA
• Among Star

An Interactive Node-Link Visualization of Convolutional Neural Networks MNIST EXAMPLE

visual effect

This paper trains a Transformer to directly predict docIDs given a search query. This means the model weights themselves are the index. What does it mean? And how viable is this for real applications?

ViT Visual Transformers

Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures DiffEdit - Semantic Image Editing with Stable Diffusion

This demo compares VQ-Diffusion-ITHQ and Stable-Diffusion-v1-5 for text to image generation.

AI PLAYGROUND A Interseção da AI, da Arte e da Ciência.

Pytorch

Word-level text generation with Keras in <50 lines of code Get the IMDB movie review dataset

Andrew NG, December 2020

Jina-powered multi-user video chat in 20 lines of code, showcasing how to use Jina for building a real-time streaming solution.