V
主页
【双语】DiT Explanation and Implementation
发布人
转载自https://www.youtube.com/watch?v=aSLDXdc2hkk [字幕由openai/whisper-large-v3-turbo + Qwen/Qwen2.5-72B-Instruct-AWQ生成(zero-shot)] In this video, we’ll dive deep into Diffusion with Transformers (DiT), a scalable approach to diffusion models that leverages the transformer architecture. We will first get an overview of vision transformer, then see the changes the author make to get to DiT. We will look in detail the different block designs that the DiT authors explore for Diffusion Transformers and also see the results of experiments with regards to diffusion transformer architecture and scaling, that the authors do. Finally we will look at an implementation of Diffusion Transformer(DiT) in Pytorch. ⏱️ Timestamps 00:00 Intro 01:10 Vision Transformer Review 04:08 From VIT to Diffusion Transformer 09:10 DiT Block Design 14:01 Experiments on DiT block and scale of Diffusion Transformer 21:50 Diffusion Transformer (DiT) implementation in PyTorch 📖 Resources Diffusion Transformer (DiT Paper) - https://tinyurl.com/exai-dit-paper My Github Implementation Link - https://tinyurl.com/exai-dit-implemen... DiT Official Implementation - https://tinyurl.com/exai-dit-official 🔔 Subscribe: https://tinyurl.com/exai-channel-link Background Track - Fruits of Life by Jimena Contreras Email - explainingai.official@gmail.com
打开封面
下载高清视频
观看高清视频
视频下载器
【双语】VQ-VAE : Explanation and Implementation
论文研读之“奶奶漏洞”为什么有效?:AI模型中的情绪刺激
【ExplainingAI】中文字幕|DiT说明与代码实现 - Scalable Diffusion Models with Transformers
【双语】Variational Autoencoders
Denoising Diffusion Models : A Generative Learning Big Bang [CVPR 2023 Tutorial]
【双语】Ilya Sutskever | Natural language realizes the whole process of conscious AI
【英字】Coding Stable Diffusion from scratch in PyTorch
【双语】Latent Space Visualisation PCA, t-SNE, UMAP
【双语】The U-Net explained in 10 minutes
【双语】Autoencoders
【双语】Score Entropy Discrete Diffusion models [ICML 2024]
【双语】Stable Diffusion from Scratch in PyTorch - Unconditional LDM
Denoising Diffusion-based Generative Modeling [CVPR 2022 Tutorial]
【双语】Auto-Encoding Variational Bayes (ICLR2024 Test of Time Award)
【双语】ControlNet with Diffusion Models - Explanation and PyTorch Implementation
【双语】Denoising Diffusion Probabilistic Models Code - DDPM Pytorch Implementation
【双语】DALL-E:Explained and Implementation
西交|深度学习研讨班-4|从Attention到Transformer再到Mamba
【双语】扩散模型原理概述 Why Does Diffusion Work Better than Auto-Regression
用ai喂出来的抽象人类
PS神器!MagicQuill:超强的图像编辑系统,这个太丝滑了!
【全100集】花2w买的SD教程!我付费,你白嫖,全程干货无废话!全网最详细的Stable Diffusion教程,存下吧,比盲目自学好多了!
【论文导读】Stable Diffusion(一):介绍
扩散模型论文概述(一):OpenAI系列工作
【双语】ICML2024-The Platonic Representation Hypothesis
【双语】CNN Receptive Field
【双语】Stable Diffusion from Scratch in PyTorch - Conditional LDM
【双语】Weak-to-Strong Generalizarion [ICML 2024]
【双语】DoRA: Weight-Decomposed Low-Rank Adaptation [ICML 2024]
【论文导读】BLIP系列(一):BLIP
【11.20-arXiv】西北工大提出物理引导的检测学习范式!2024年11月20日arXiv cs.CV发文量约106余篇,减论Agent通过算法为您推荐!
【双语】Language Models as World Models
【双语】Denoising Diffusion Probabilistic Models - Explained
【双语】Direct Preference Optimization [NeurIPS 2023]
【论文导读】BLIP系列(四):BLIP-3
【论文导读】RemoteCLIP: A vision language foundation model for remote sensing
超越GPT-4o mini!北大开源国产多模态版o1,超强视觉推理惊呆网友
【论文导读】Qwen2-VL
【双语】Deep Generative Models | Lecture 1 - Introduction
【论文导读】Stable Diffusion(二):相关工作