Flipboard

NOVEMBER 29, 2023

Even at home, SDXL Turbo can create detailed images with startling speed. On Tuesday, Stability AI launched Stable Diffusion XL Turbo, an AI …

AI 178

AI AI Computer Science Computer Science 178

Flipboard

JULY 13, 2023

Stability AI, the startup behind the image-generating model Stable Diffusion, is launching a new service that turns sketches into images. The sketch-to-image service, Stable Doodle, leverages the latest Stable Diffusion model to analyze the outline of a sketch and generate a “visually pleasing” …

AI 123

AI AI Computer Science Computer Science 123

Dataconomy

DECEMBER 13, 2023

In the diverse arena of AI image generators, Tensor Art emerges as a cool and effective option , distinguishing itself by enabling users to create images with Stable Diffusion. Tensor Art stands as a cutting-edge AI image generator, enabling users to craft bespoke artistic creations.

AI 113

AI AI Artificial Intelligence Artificial Intelligence 113

Flipboard

DECEMBER 8, 2023

DemoFusion is a new artificial intelligence model that can generate much higher resolution images than is possible with tools like Stable Diffusion and Midjourney.

Artificial Intelligence 148

Artificial Intelligence Artificial Intelligence AI AI 148

FlowingData

SEPTEMBER 8, 2022

People have been having fun with the text-to-image generators lately. Enter a description, and the AI churns out believable and sometimes detailed images that match the input. The reason these systems work is because the models were trained on a lot of data, in the form of images.

AI 96

AI AI 96

Analytics Vidhya

FEBRUARY 24, 2024

Stability AI has announced the arrival of Stable Diffusion 3, the latest advancement in AI imagery technology. This new model promises significant improvements in text-to-image generation, boasting enhanced performance and quality.

AI 274

AI AI Analytics Analytics 274

Analytics Vidhya

JANUARY 22, 2024

Introduction Stability AI has been at the forefront of developing Open Source Diffusion Models like the Stable Diffusion and Stable Diffusion XL, which have brought a revolution to the field of text-to-image generation.

Analytics 242

Analytics Analytics AI AI 242

Machine Learning Mastery

APRIL 27, 2024

ControlNet is a neural network that can improve image generation in Stable Diffusion by adding extra conditions. This allows users to have more control over the images generated. Instead of trying out different prompts, the ControlNet models enable users to generate consistent images with just one prompt.

236

236

Flipboard

MARCH 6, 2023

Researchers have been able to use Stable Diffusion models to reconstruct images from human brain waves. Imagine having the ability to recall your …

AI 123

AI AI Artificial Intelligence Artificial Intelligence 123

Flipboard

FEBRUARY 6, 2023

Getty Images has filed a case against Stability AI, alleging that the company copied 12 million images to train its AI model ‘without permission. Getty Images has filed a lawsuit in the US against Stability AI, creators of open-source AI art generator Stable Diffusion, … or compensation.’

AI 123

AI AI Artificial Intelligence Artificial Intelligence 123

Machine Learning Mastery

MAY 3, 2024

OpenPose is a great tool that can detect body keypoint locations in images and video. By integrating OpenPose with Stable Diffusion, we can guide the AI in generating images that match specific poses. In […] The post Using OpenPose with Stable Diffusion appeared first on MachineLearningMastery.com.

AI 224

AI AI 224

BAIR

MAY 23, 2023

TL;DR : Text Prompt -> LLM -> Intermediate Representation (such as an image layout) -> Stable Diffusion -> Image. Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. Both stages are training-free.

145

145

Analytics Vidhya

MAY 24, 2023

Introduction By applying specific modern state-of-the-art techniques, stable diffusion models make it possible to generate images and audio. Stable Diffusion works by modifying input data with the guide of text input and generating new creative output data.

Analytics 290

Analytics Analytics Deep Learning Deep Learning 290

Flipboard

NOVEMBER 29, 2023

A new artificial intelligence image generator that can create a new image in real-time has been released by Stable Diffusion makers StabilityAI. …

Artificial Intelligence 67

Artificial Intelligence Artificial Intelligence AI AI 67

Analytics Vidhya

DECEMBER 28, 2023

The integrity of a major AI image training dataset, LAION-5B, utilized by influential AI models like Stable Diffusion, has been compromised after the discovery of thousands of links to Child Sexual Abuse Material (CSAM).

AI 248

AI AI Analytics Analytics 248

Hacker News

MARCH 2, 2024

[WIP] Layer Diffusion for WebUI (via Forge). Contribute to layerdiffusion/sd-forge-layerdiffusion development by creating an account on GitHub.

140

140

Machine Learning Mastery

APRIL 24, 2024

Inpainting and outpainting have long been popular and well-studied image processing domains. However, recent advancements in the form of Stable diffusion have reshaped these domains. Traditional approaches to these problems often relied on complex algorithms and deep learning techniques yet still gave inconsistent outputs.

Deep Learning 190

Deep Learning Deep Learning Algorithm 190

Analytics Vidhya

DECEMBER 29, 2023

Introduction With the recent advancement in AI, the capabilities of Generative AI are being explored, and generating images from text is one such capability. Many models include Stable Diffusion, Imagen, Dall-E 3, Midjourney, Dreambooth, DreamFusion, and many more.

Analytics 288

Analytics Analytics AI AI 288

Analytics Vidhya

MAY 29, 2023

Introduction Hugging face has provided different means of carryout image-to-image generation using pre-trained models and other available libraries. This article will generate new images from an input image using UNet2DConditionModel models. The implementation will be based on PyTorch and then the hugging face depth2img.

Analytics 291

Analytics Analytics 291

Machine Learning Mastery

MAY 5, 2024

The image diffusion model, in its simplest form, generates an image from the prompt. The prompt can be a text prompt or an image as long as a suitable encoder is available to convert it into a tensor that the model can use as a condition to guide the generation process.

198

198

Analytics Vidhya

MARCH 27, 2024

MIT researchers have made a significant breakthrough in AI image generation. They’ve developed a technique called “distribution matching distillation” (DMD) that can make popular AI image generators like DALL-E 3 and Stable Diffusion run up to 30 times faster.

AI 270

AI AI Analytics Analytics 270

KDnuggets

DECEMBER 15, 2023

You learned how to generate images using the base model, how to upgrade to the Stable Diffusion XL model to improve image quality, and how to use a custom model to generate high quality portraits.

Artificial Intelligence 285

Artificial Intelligence Artificial Intelligence 285

Analytics Vidhya

FEBRUARY 29, 2024

Fractal, a prominent provider of AI solutions, has made waves with the launch of Kalaido.ai, India’s pioneering text-to-image diffusion model. This innovative tool promises to revolutionize image generation by catering to diverse linguistic needs and offering unmatched efficiency.

AI 261

AI AI Analytics Analytics 261

Hacker News

APRIL 5, 2024

text-to-image generation model was recently released that generates small artifacts in the image when the earlier 0.9 The new SDXL 1.0 release didn't have them.

114

114

Machine Learning Mastery

APRIL 6, 2024

Although prior models existed in the image generation space, it’s the GenAI wave that caught everyone’s attention. Stable Diffusion is a member of the […] The post A Technical Introduction to Stable Diffusion appeared first on MachineLearningMastery.com.

AI 202

AI AI 202

Machine Learning Mastery

APRIL 14, 2024

Generating pictures using Stable Diffusion in all cases would involve to submit a prompt to the pipeline. An incomplete or poorly constructed prompt would make the resulting image not as you would expect. This is only one of the parameters, but the most important one.

183

183

Machine Learning Mastery

APRIL 14, 2024

Generating pictures using Stable Diffusion in all cases would involve to submit a prompt to the pipeline. An incomplete or poorly constructed prompt would make the resulting image not as you would expect. This is only one of the parameters, but the most important one.

155

155

Analytics Vidhya

NOVEMBER 21, 2023

Introduction Segmind AI has proudly presented SSD-1B (Segmind Stable Diffusion 1B), a groundbreaking open-source text-to-image revolution of generative model. The SSD 1B […] The post Text-to-Image Revolution: Segmind’s SD-1B Model Emerges as the Fastest in the Game appeared first on Analytics Vidhya.

Natural Language Processing 285

Natural Language Processing Artificial Intelligence Artificial Intelligence Analytics 285

Analytics Vidhya

NOVEMBER 8, 2023

Introduction 2023 has been an AI year, from language models to stable diffusion models. It is a multimodal large language model (MLLM) making waves with groundbreaking capabilities in understanding text and images. One of the new players that has taken center stage is the KOSMOS-2, developed by Microsoft.

Analytics 302

Analytics Analytics AI AI 302

Hacker News

FEBRUARY 22, 2024

Announcing Stable Diffusion 3 in early preview, our most capable text-to-image model with greatly improved performance in multi-subject prompts, image quality, and spelling abilities.

182

182

Hacker News

MARCH 20, 2024

Robin Rombach and a group of key researchers that helped develop the Stable Diffusion text-to-image generation model have left the troubled generative AI startup.

AI 182

AI AI 182

Flipboard

FEBRUARY 6, 2023

The stock image site is seeking millions of dollars in damages, alleging Stability AI broke copyright and abused Getty's logo in generated images.

AI 123

AI AI Artificial Intelligence Artificial Intelligence 123

Machine Learning Research at Apple

NOVEMBER 7, 2022

Today, we are excited to release optimizations to Core ML for Stable Diffusion in macOS 13.1 Figure 1: Images generated with the prompts, "a high quality photo of an astronaut riding a (horse/dragon) in space" using Stable Diffusion and Core ML + diffusers running on-device on Apple Silicon.}> and iOS 16.2,

ML 242

ML ML 242

Analytics Vidhya

SEPTEMBER 5, 2022

See that image above? The post Stable Diffusion AI has Taken the World By Storm appeared first on Analytics Vidhya. This article was published as a part of the Data Science Blogathon. Amazing, isn’t it? Looks like an oil painting in melancholic postcard style, right? And we will see […].

AI 234

AI AI Data Science Analytics 234

Hacker News

JANUARY 28, 2024

Stable Diffusion may soon have some competition when it comes to open-source image generators. In its latest iteration, PixArt becomes faster and more accurate while maintaining a relatively high resolution.

AI 169

AI AI 169

Flipboard

FEBRUARY 13, 2023

Medical doctors who specialize in rare diseases get only so many opportunities to learn as they go. The lack of diverse healthcare data to train students is a key challenge in these fields. When you are working in a setting with scarce data, your performance correlates with experience — the more …

Artificial Intelligence 114

Artificial Intelligence Artificial Intelligence Machine Learning Machine Learning 114

Towards AI

MARCH 6, 2024

The recent publication of the Stable Diffusion 3 paper has brought exciting news! Upon evaluation, Stable Diffusion 3 has surpassed other leading systems in text-to-image generation, including DALL·E 3, Midjourney v6, and Ideogram v1. Stable Diffusion 3 draws inspiration from the Latent Diffusion Transformer architecture.

AI 101

AI AI Machine Learning Machine Learning 101