Главная
Study mode:
on
1
Intro
2
VQGAN overview
3
Conditioning in VQGAN
4
BART transformer
5
DALL-E 1 overview
6
DALL-E mini Weights & Biases report
7
[code] min-dalle
8
Text tokenizer
9
BART encoder
10
GLU explained paper + code
11
BART decoder
12
Image latent vector autoregressive generation
13
Super conditioning, top-k sampling
14
VQGAN decoder
15
Outro
Description:
Dive into a comprehensive video tutorial exploring the DALL-E mini project, an open-source implementation of DALL-E. Begin with an overview of essential concepts including VQ-GAN, BART, GLU, and DALL-E papers. Examine the Weights & Biases report on DALL-E mini before delving into the actual code. Learn about text tokenization, BART encoder and decoder, GLU (Gated Linear Units), image latent vector autoregressive generation, super conditioning, top-k sampling, and VQGAN decoder. Gain insights into the inner workings of AI-powered image generation models through this in-depth exploration of min(DALL-E), the minimal PyTorch port of DALL-E mini.

DALL-E Mini Explained - ML Coding Series

Aleksa Gordić - The AI Epiphany
Add to list
0:00 / 0:00