Scribble Diffusion: Transform Your Sketches into Refined Images

Scribble Diffusion: Transform Your Sketches into Refined Images

Today, I want to talk about a recently popular innovative AI tool – Scribble Diffusion. Just how amazing is this tool? In simple terms, it can quickly generate exquisite, high-definition images from the initial sketches provided by users, almost like adding magic to doodles. And the best part is, it not only enhances the sketches … Read more

First 4D Video Generation Diffusion Model! Diffusion4D Achieves 4D Content Generation in Minutes with Over 81K Open-Sourced 4D Dataset!

First 4D Video Generation Diffusion Model! Diffusion4D Achieves 4D Content Generation in Minutes with Over 81K Open-Sourced 4D Dataset!

Follow our public account to discover the beauty of CV technology This article introduces the latest 4D generation diffusion model proposed by teams from the University of Toronto, Beijing Jiaotong University, the University of Texas at Austin, and the University of Cambridge. This method can achieve spatio-temporal consistent 4D content generation in just a few … Read more

Understanding Diffusion Models in Simple Terms

Understanding Diffusion Models in Simple Terms

In 2022, the rapid development of AIGC in the field of large language models made general artificial intelligence seem less distant. When the number of parameters exceeds a certain threshold, AIGC systems based on large language models can understand commands issued by humans in natural language and correspondingly generate real, high-quality text, images, audio, video, … Read more

Stable Diffusion Online: A Free Open-Source Multi-Functional AI Drawing Model

Stable Diffusion Online: A Free Open-Source Multi-Functional AI Drawing Model

Today, let’s talk about the Stable Diffusion model—a deep learning model that can directly generate images from text descriptions. This technology has been highly popular in the past two years for a simple reason: it not only can ‘draw’ based on text descriptions, but the generated images are also very realistic. If you are interested … Read more

Peking University Team Upgrades DragGAN with Diffusion for Enhanced Image Generation

Peking University Team Upgrades DragGAN with Diffusion for Enhanced Image Generation

Follow Our Official Account to Discover the Beauty of CV Technology The latest work from the Peking University team demonstrates that diffusion models can also achieve drag-and-drop image editing! With just a click, you can make a snow mountain grow taller: Or make the sun rise: This is DragonDiffusion, brought to you by Professor Zhang … Read more

Understanding Diffusion Model in AI

Understanding Diffusion Model in AI

MLNLP community is a well-known machine learning and natural language processing community at home and abroad, covering NLP master’s and doctoral students, university teachers, and corporate researchers. The vision of the community is to promote communication and progress between the academic and industrial circles of natural language processing and machine learning at home and abroad, … Read more

Understanding Stable Diffusion Principles in Simple Terms

Understanding Stable Diffusion Principles in Simple Terms

MLNLP Community is a well-known machine learning and natural language processing community in China and abroad, covering NLP master’s and PhD students, university teachers, and corporate researchers. Community Vision is to promote communication and progress between the academic and industrial circles of natural language processing and machine learning, especially for beginners. Reprinted from | Zhihu … Read more

Is Diffusion Really Stronger Than GAN?

Is Diffusion Really Stronger Than GAN?

AI painting is one of the branches of AIGC, amidst the hype and controversy, in 2022 it was even dubbed the “AIGC Year.” As AI painting exploded, one of its core technologies, Diffusion Model, has also gained immense popularity in the field of image generation, even showing signs of starting to surpass GAN. From the … Read more

A Simple Trick to Improve LLaMa3’s Honesty by 65%

A Simple Trick to Improve LLaMa3's Honesty by 65%

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering audiences including NLP master’s and doctoral students, university teachers, and researchers from enterprises. The vision of the community is to promote communication and progress between the academic and industrial fields of natural language processing and machine learning, especially … Read more

LLaMA-2-7B Achieves 97.7% Math Ability? Xwin-Math Unlocks Potential with Synthetic Data

LLaMA-2-7B Achieves 97.7% Math Ability? Xwin-Math Unlocks Potential with Synthetic Data

Source: Machine Heart This article is about 1600 words long, suggested reading time is 5 minutes. Synthetic data continues to unlock the mathematical reasoning potential of large models! The ability to solve mathematical problems has always been regarded as an important indicator of the intelligence level of language models. Typically, only models that are extremely … Read more