Stable Diffusion

14 Posts

Synthetic Data Helps Image Classification: StableRep, a method that trains vision transformers on images generated by Stable Diffusion
Stable Diffusion

Synthetic Data Helps Image Classification: StableRep, a method that trains vision transformers on images generated by Stable Diffusion

Generated images can be more effective than real ones in training a vision model to classify images. Yonglong Tian, Lijie Fan, and colleagues at Google and MIT introduced StableRep, a self-supervised method that trains vision transformers on images generated by...
Graphic model of Stable Audio difffusion and transcoding process
Stable Diffusion

Music Generation For the Masses: Stability.ai launches Stable Audio, a text-to-music generator.

Stability.ai, maker of the Stable Diffusion image generator and StableLM text generator, launched Stable Audio, a system that generates music and sound effects from text. You can play with it and listen to examples here. The service is free for 20 generations per month up to 45 seconds long.
Text-To-3D Animation: MAV3D, a method for generating 3D dynamic scenes from text descriptions
Stable Diffusion

Text-To-3D Animation: MAV3D, a method for generating 3D dynamic scenes from text descriptions

Text-to-video generation is so 2022! A new system takes in text and generates an animated 3D scene that can be viewed or rendered from any angle.
Diffusion Transformed: A new class of diffusion models based on the transformer architecture
Stable Diffusion

Diffusion Transformed: A new class of diffusion models based on the transformer architecture

A tweak to diffusion models, which are responsible for most of the recent excitement about AI-generated images, enables them to produce more realistic output.
Stable Biases: Stable Diffusion may amplify biases in its training data.
Stable Diffusion

Stable Biases: Stable Diffusion may amplify biases in its training data.

Stable Diffusion may amplify biases in its training data in ways that promote deeply ingrained social stereotypes.
What the Brain Sees: How a text-to-image model generates images from brain scans
Stable Diffusion

What the Brain Sees: How a text-to-image model generates images from brain scans

A pretrained text-to-image generator enabled researchers to see — roughly — what other people looked at based on brain scans. Yu Takagi and Shinji Nishimoto developed a method that uses Stable Diffusion to reconstruct images viewed by test subjects...
Like Diffusion but Faster: The Paella model for fast image generation, explained
Stable Diffusion

Like Diffusion but Faster: The Paella model for fast image generation, explained

The ability to generate realistic images without waiting would unlock applications from engineering to entertainment and beyond. New work takes a step in that direction.
LAION Roars: The story of LAION, the dataset behind Stable Diffusion
Stable Diffusion

LAION Roars: The story of LAION, the dataset behind Stable Diffusion

The largest dataset for training text-to-image generators was assembled by volunteers for roughly $10,000. Now it’s implicated in fights over whether copyrighted works can be used for training.
Text-to-Image Editing Evolves: InstructPix2Pix for text-to-image editing, explained
Stable Diffusion

Text-to-Image Editing Evolves: InstructPix2Pix for text-to-image editing, explained

Text-to-image generators like DALL·E 2, Stable Diffusion, and Adobe’s new Generative Fill feature can revise images in a targeted way — say, change the fruit in a bowl from oranges to bananas — if you enter a few words that describe the change plus an indication of the areas to be changed.
Architect’s Sketchbook: How a top architecture firm is using generative AI
Stable Diffusion

Architect’s Sketchbook: How a top architecture firm is using generative AI

Text-to-image generators are visualizing the next wave of architectural innovation. Patrick Schumacher, principal architect at Zaha Hadid Architects, explained how the company uses generative AI to come up with ideas. He made the remarks at an industry roundtable called AI and the Future of Design.
Don’t Steal My Style: Glaze tool prevents AI from learning an artist's style.
Stable Diffusion

Don’t Steal My Style: Glaze tool prevents AI from learning an artist's style.

Asked to produce “a landscape by Thomas Kinkade,” a text-to-image generator fine-tuned on the pastoral painter’s work can mimic his style in seconds, often for pennies. A new technique aims to make it harder for algorithms to mimic an artist’s style.
Illustration of an elf workshop creating a red toy car from a description (channeling AI generated images)
Stable Diffusion

Synthetic Images Everywhere: 2022 was the year text-to-image AI went mainstream.

Pictures produced by AI went viral, stirred controversies, and drove investments. A new generation of text-to-image generators inspired a flood of experimentation, transforming text descriptions into mesmerizing artworks and photorealistic fantasies.
Screen capture of question in DeviantArt about consent of the use of artwork by AI datasets
Stable Diffusion

Creatives Fight Back: Generative AI from DeviantArt Creates Controversy

Artists are rebelling against AI-driven imitation. DeviantArt, an online community where artists display and sell their work and marketplace for digital art, launched DreamUp, a text-to-image generator that aims to help artists thwart attempts to imitate their styles or works.
Captures from PromptBase
Stable Diffusion

Prompting DALL·E for Fun and Profit: A marketplace for phrases that produce art in DALL·E, Midjourney, and Stable Diffusion

An online marketplace enables people to buy text prompts designed to produce consistent output from the new generation of text-to-image generators.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox