Programming Generative Ai

[xodynu]

Programming Generative Ai
Released 10/2024
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz, 2 Ch
Genre: eLearning | Language: English | Duration: 18h 16m | Size: 4.1 GB
From variational autoencoders to Stable Diffusion with PyTorch and Hugging Face.
Overview​

Programming Generative AI is a hands-on tour of deep generative modeling, taking you from building simple feedforward neural networks in PyTorch all the way to working with large multimodal models capable of simultaneously understanding text and images. Along the way, you will learn how to train your own generative models from scratch to create an infinity of images, generate text with large language models similar to the ones that power applications like ChatGPT, write your own text-to-image pipeline to understand how prompt- based generative models actually work, and personalize large pretrained models like stable diffusion to generate images of novel subjects in unique visual styles (among other things).
About the Instructor
Jonathan Dinu is currently a content creator and artist working with deep learning and generative AI. Previously, he was a PhD student at Carnegie Mellon University before dropping out to ultimately pursue the less academic and more creative side of machine learning. He has always loved creating educational content, going back to his days as a co-founder of Zipfian Academy, an immersive data science bootcamp, where he had the opportunity to run workshops at major conferences like O'Reilly Strata and PyData, create video courses, and teach in person.
Skill Level
Intermediate to advanced
Learn How To
Train a variational autoencoder with PyTorch to learn a compressed latent space of images
Generate and edit realistic human faces with unconditional diffusion models and SDEdit
Use large language models such as GPT2 to generate text with Hugging Face Transformers
Perform text-based semantic image search using multimodal models such as CLIP
Program your own text-to-image pipeline to understand how prompt-based generative models such as Stable Diffusion actually work
Properly evaluate generative models, both qualitatively and quantitatively
Automatically caption images using pretrained foundation models
Generate images in a specific visual style by efficiently fine-tuning Stable Diffusion with LoRA.
Create personalized AI avatars by teaching pretrained diffusion models new subjects and concepts with Dreambooth.
Guide the structure and composition of generated images using depth- and edge- conditioned ControlNets
Perform near real-time inference with SDXL Turbo for frame-based video-to-video translation
Who Should Take This Course
Engineers and developers interested in building generative AI systems and applications
Data scientists interested in working with state-of-the-art deep learning models
Students, researchers, and academics looking for an applied or hands-on resource to complement theoretical or conceptual knowledge they may have.
Technical artists and creative coders who want to augment their creative practice
Anyone interested in working with generative AI who does not know where or how to start
Course Requirements
Comfortable programming in Python
Knowledge of machine learning basics
Familiarity with deep learning and neural networks will be helpful but is not required
Screenshot

Bitte Anmelden oder Registrieren um Code Inhalt zu sehen!

 

[0dayddl]

4.05 GB | 00:23:56 | mp4 | 1280X720 | 16:9
Genre:eLearning |Language:English​

Files Included :

Spoiler

1 1 Generative AI in the Wild (67.53 MB)
1 2 Defining Generative AI (23.61 MB)
1 3 Multitudes of Media (41.42 MB)
1 4 How Machines Create (49.17 MB)
1 5 Formalizing Generative Models (56.96 MB)
1 6 Generative versus Discriminative Models (42.33 MB)
1 7 The Generative Modeling Trilemma (31.2 MB)
1 8 Introduction to Google Colab (115.35 MB)
2 10 Working with Devices (53.56 MB)
2 11 Components of a Learning Algorithm (23.35 MB)
2 12 Introduction to Gradient Descent (24.2 MB)
2 13 Getting to Stochastic Gradient Descent (SGD) (15 MB)
2 14 Comparing Gradient Descent and SGD (29.22 MB)
2 15 Linear Regression with PyTorch (129.91 MB)
2 16 Perceptrons and Neurons (31.42 MB)
2 17 Layers and Activations with torch nn (62.29 MB)
2 18 Multi-layer Feedforward Neural Networks (MLP) (46.68 MB)
2 1 What Is PyTorch (17.78 MB)
2 2 The PyTorch Layer Cake (36.72 MB)
2 3 The Deep Learning Software Trilemma (24 MB)
2 4 What Are Tensors, Really (22.42 MB)
2 5 Tensors in PyTorch (38.73 MB)
2 6 Introduction to Computational Graphs (25.07 MB)
2 7 Backpropagation Is Just the Chain Rule (34.72 MB)
2 8 Effortless Backpropagation with torch autograd (55.79 MB)
2 9 PyTorch's Device Abstraction (i e , GPUs) (12.4 MB)
3 10 Setting up a Training Loop (33.95 MB)
3 11 Inference with an Autoencoder (18.12 MB)
3 12 Look Ma, No Features! (32.93 MB)
3 13 Adding Probability to Autoencoders (VAE) (17.57 MB)
3 14 Variational Inference Not Just for Autoencoders (28.92 MB)
3 15 Transforming an Autoencoder into a VAE (34.86 MB)
3 16 Training a VAE with PyTorch (35.49 MB)
3 17 Exploring Latent Space (40.63 MB)
3 18 Latent Space Interpolation and Attribute Vectors (37.49 MB)
3 1 Representing Images as Tensors (35.04 MB)
3 2 Desiderata for Computer Vision (22.46 MB)
3 3 Features of Convolutional Neural Networks (29.83 MB)
3 4 Working with Images in Python (51.03 MB)
3 5 The FashionMNIST Dataset (16.92 MB)
3 6 Convolutional Neural Networks in PyTorch (40.25 MB)
3 7 Components of a Latent Variable Model (LVM) (36.54 MB)
3 8 The Humble Autoencoder (19.92 MB)
3 9 Defining an Autoencoder with PyTorch (20.11 MB)
4 10 Image Restoration and Enhancement (38.06 MB)
4 1 Generation as a Reversible Process (17.29 MB)
4 2 Sampling as Iterative Denoising (19.96 MB)
4 3 Diffusers and the Hugging Face Ecosystem (34.64 MB)
4 4 Generating Images with Diffusers Pipelines (97.61 MB)
4 5 Deconstructing the Diffusion Process (81.29 MB)
4 6 Forward Process as Encoder (67.45 MB)
4 7 Reverse Process as Decoder (28.51 MB)
4 8 Interpolating Diffusion Models (49.31 MB)
4 9 Image-to-Image Translation with SDEdit (27.56 MB)
5 10 Embedding Sequences with Transformers (30.25 MB)
5 11 Computing the Similarity Between Embeddings (23.57 MB)
5 12 Semantic Search with Embeddings (23.3 MB)
5 13 Contrastive Embeddings with Sentence Transformers (20.23 MB)
5 1 The Natural Language Processing Pipeline (44.54 MB)
5 2 Generative Models of Language (39.8 MB)
5 3 Generating Text with Transformers Pipelines (48.1 MB)
5 4 Deconstructing Transformers Pipelines (30.54 MB)
5 5 Decoding Strategies (37.7 MB)
5 6 Transformers are Just Latent Variable Models for Sequences (42.94 MB)
5 7 Visualizing and Understanding Attention (56.29 MB)
5 8 Turning Words into Vectors (51.75 MB)
5 9 The Vector Space Model (24.15 MB)
6 10 Failure Modes and Additional Tools (29.2 MB)
6 11 Stable Diffusion Deconstructed (37.8 MB)
6 12 Writing Our Own Stable Diffusion Pipeline (31.76 MB)
6 13 Decoding Images from the Stable Diffusion Latent Space (14.03 MB)
6 14 Improving Generation with Guidance (26.07 MB)
6 15 Playing with Prompts (120.71 MB)
6 1 Components of a Multimodal Model (16.06 MB)
6 2 Vision-Language Understanding (38.14 MB)
6 3 Contrastive Language-Image Pretraining (20.81 MB)
6 4 Embedding Text and Images with CLIP (41.24 MB)
6 5 Zero-Shot Image Classification with CLIP (11.95 MB)
6 6 Semantic Image Search with CLIP (40.9 MB)
6 7 Conditional Generative Models (24.74 MB)
6 8 Introduction to Latent Diffusion Models (33.43 MB)
6 9 The Latent Diffusion Model Architecture (23.43 MB)
7 10 Conceptual Overview of Textual Inversion (33.09 MB)
7 11 Subject-Specific Personalization with Dreambooth (33.14 MB)
7 12 Dreambooth versus LoRA Fine-Tuning (22.83 MB)
7 13 Dreambooth Fine-Tuning with Hugging Face (47.62 MB)
7 14 Inference with Dreambooth to Create Personalized AI Avatars (51.16 MB)
7 15 Adding Conditional Control to Text-to-Image Diffusion Models (16.3 MB)
7 16 Creating Edge and Depth Maps for Conditioning (58.39 MB)
7 17 Depth and Edge-Guided Stable Diffusion with ControlNet (68.81 MB)
7 18 Understanding and Experimenting with ControlNet Parameters (35.82 MB)
7 19 Generative Text Effects with Font Depth Maps (7.07 MB)
7 1 Methods and Metrics for Evaluating Generative AI (22.35 MB)
7 20 Few Step Generation with Adversarial Diffusion Distillation (ADD) (33.79 MB)
7 21 Reasons to Distill (18.06 MB)
7 22 Comparing SDXL and SDXL Turbo (37.58 MB)
7 23 Text-Guided Image-to-Image Translation (72.66 MB)
7 24 Video-Driven Frame-by-Frame Generation with SDXL Turbo (78.73 MB)
7 25 Near Real-Time Inference with PyTorch Performance Optimizations (32.17 MB)
7 2 Manual Evaluation of Stable Diffusion with DrawBench (54.21 MB)
7 3 Quantitative Evaluation of Diffusion Models with Human Preference Predictors (63.47 MB)
7 4 Overview of Methods for Fine-Tuning Diffusion Models (22.83 MB)
7 5 Sourcing and Preparing Image Datasets for Fine-Tuning (23.58 MB)
7 6 Generating Automatic Captions with BLIP-2 (21.46 MB)
7 7 Parameter Efficient Fine-Tuning with LoRA (45.43 MB)
7 8 Inspecting the Results of Fine-Tuning (16.02 MB)
7 9 Inference with LoRAs for Style-Specific Generation (42.53 MB)
Programming Generative AI Introduction (1) (24.87 MB)
Programming Generative AI Introduction (24.87 MB)
Programming Generative AI Summary (4.81 MB)
Topics (1) (4.27 MB)
Topics (2) (4.54 MB)
Topics (3) (4.52 MB)
Topics (4) (4.01 MB)
Topics (5) (4.22 MB)
Topics (6) (4.25 MB)
Topics (3.83 MB)

]
Screenshot

Spoiler

Fikper

Bitte Anmelden oder Registrieren um Code Inhalt zu sehen!

FileAxa

Bitte Anmelden oder Registrieren um Code Inhalt zu sehen!

RapidGator

Bitte Anmelden oder Registrieren um Code Inhalt zu sehen!

TurboBit

Bitte Anmelden oder Registrieren um Code Inhalt zu sehen!