List: Sora and Diffusion Models | Curated by CP Lu, PhD

May 16, 2024
20 stories
1 save
Sora and Diffusion Models
In
DataDrivenInvestor
by
Devansh
Will Diffusion Models be The Next Frontier of Deep LearningAlphaFold 3, LLMs and much more are using diffusion to improve performance
May 11, 2024
2
May 11, 2024
2
Aaron 0928
OpenAI’s Sora is doomed to die ?Yann LeCun fires up: this implementation is “completely unrealistic”!
Feb 24, 2024
2
Feb 24, 2024
2
In
Kinomoto.Mag AI
by
Filipa Kinomoto
Adobe to Integrate AI Video Generators Sora, Runway, Pika into Premiere ProIn a bold move, Adobe announced plans to enhance Premiere Pro by integrating plug-ins for emerging third-party AI video generator models…
Apr 19, 2024
1
Apr 19, 2024
1
In
TDS Archive
by
Nikita Kiselov
State of Video GenerationOverview of latest developments in the Video Generation area:  From LLMs to MultyDiffusion. Paper’s insights and Outstanding questions.
Feb 16, 2024
2
Feb 16, 2024
2
In
TDS Archive
by
Sascha Kirch
The Rise of Diffusion Models — A new Era of Generative Deep LearningDenoising Diffusion Probabilistic Models by J. Ho et. al.
Mar 27, 2024
2
Mar 27, 2024
2
In
Towards AI
by
Jesus Rodriguez
Inside Genie: Google DeepMind’s Super Model that can Generate Interactive Games from Text and…The model represents a major breakthrough in generative AI.
Mar 4, 2024
2
Mar 4, 2024
2
 This story is no longer available
In
The Deep Hub
by
RickyYang
Exploring the Core: A Technical Deep Dive into OpenAI’s Sora ModelIn recent days, the tech community has been abuzz with news of OpenAI’s groundbreaking model, Sora, capable of generating one-minute videos…
Feb 19, 2024
Feb 19, 2024
DataStax
Building an Image Search App with a Vector Database and CLIP ModelsBy Aaron Ploetz
Feb 6, 2024
Feb 6, 2024
In
Level Up Coding
by
Salvatore Raieli
Unlocking the Dance of Proteins: AlphaFold meets DiffusionAlphaFlow Makes Protein Structure PredictionFrom Static to Dynamic
Feb 27, 2024
2
Feb 27, 2024
2
In
Towards AI
by
Ignacio de Gregorio
GLIGEN, the Tool to Rule All AI Image GeneratorsThe Grounding Problem Solved?
Feb 27, 2024
9
Feb 27, 2024
9
In
The Generator
by
Thomas Smith
Why OpenAI’s Sora Is About Way More Than AI VideosA world in silicon
Feb 26, 2024
21
Feb 26, 2024
21
In
Generative AI
by
Jim Clyde Monge
Stable Diffusion 3 Is Here — It’s Packed With Huge ImprovementsIt uses a similar tech to Sora, can generate text, and has improved performance and image quality.
Feb 22, 2024
6
Feb 22, 2024
6
In
Towards AI
by
Jesus Rodriguez
Inside OpenAI Sora: Five Key Technical Details We Learned About the Amazing Video Generation ModelThe magical text-to-video model is powered by some key technical innovations.
Feb 20, 2024
1
Feb 20, 2024
1
In
The Generator
by
John B. Dutton
Que Sora, Sora? Is OpenAI’s New Text-To-Video Model As Amazing As It Seems?Should Hollywood worry that it will soon be put out of business?
Feb 19, 2024
10
Feb 19, 2024
10
Ozgur Guler
昊 SORA  for the transformer challangedSORA Debate — Generation vs causal prediction
Feb 18, 2024
Feb 18, 2024
Ignacio de Gregorio
Demystifying OpenAI’s Stunning New Model SoraSora, the astonishing yet dumb model?
Feb 19, 2024
12
Feb 19, 2024
12
In
TDS Archive
by
Vincent Koc
Explaining OpenAI Sora’s Spacetime Patches: The Key IngredientUnder The Hood Of The Generative AI For Video By OpenAI
Feb 16, 2024
5
Feb 16, 2024
5
In
AI Blog TW
by
Jia-Yau Shiau
實作理解Diffusion Model: 來自DDPM的簡化概念Diffusion model是一個透過變分推斷 (Variational Inference) 訓練的參數化馬可夫鍊 (Markov Chain)，並且在許多任務上展現了超越 GAN的效果，其中最知名的應用莫過於 OpenAI的 DALL-E 2與 Google…
May 31, 2022
2
May 31, 2022
2
In
AI Blog TW
by
Jia-Yau Shiau
Stable Diffusion背後的技術：高效、高解析又易控制的Latent Diffusion Model近年，生成式模型 (generative model) 用於圖像生成展現了驚人的成果，最知名的莫過於基於 diffusion model 的 Stable Diffusion 與 Midjourney。雖然目前還無法完整地指出 Midjourney 背後的方法，但透過…
Apr 16, 2023
Apr 16, 2023