image generation

Alex O'Connor shows that ChatGPT cannot draw a wine glass filled to the brim, and ties the failure to David Hume's missing shade of blue. It asks what the failure says about how image models learn.

A guest video by Welch Labs on 3Blue1Brown explaining how text-to-image and video models work. It covers CLIP, shared embedding spaces, diffusion models (DDPM, DDIM), conditioning, guidance and negative prompts.

Herbert Wolverson's Roguelike Celebration 2020 talk surveying procedural map generation techniques, including integration of hand-crafted prefabs and vaults.

A short explainer from Nat and Friends on where Google Earth's 3D imagery comes from, how it is stitched together, and how often it is updated. It describes aircraft carrying camera rigs and photogrammetry that turns the photos into 3D models.

A six-minute clip of Adobe's MAX 2011 sneak peek showing a Photoshop prototype that removes motion blur from photos. The audience reacts with astonishment as blurry images become legible.

A short demo of an open-source Krita plugin that uses Stable Diffusion to generate and edit images in place. It adds ControlNet scribble and line-art support. You select an area, push a button, and new matching content appears.

Ubisoft procedural technical artist Etienne Carrier explains the Houdini-based tools used to build Far Cry 5's roughly 100 square km open world. It covers generating biomes, texturing terrain, freshwater networks, cliff rocks and vegetation placement.

OpenAI's 2021 live demo of Codex translating natural language into code, from Hello World to building a game and a Microsoft Word plugin.

Michael Levin's NeurIPS 2018 talk on bioelectric computation outside the nervous system, showing how cell electrical networks shape development and regeneration. It covers morphological information processing in living tissue.

Adam Conover's talk at a millennial marketing conference argues that generations are an unscientific, condescending idea and that millennials do not exist as a real category. The description notes that researcher Jean Twenge later said he misrepresented some of her work.

The Thought Emporium shows how to receive clear images directly from GOES-15, 16 and 17 and Himawari 8 geostationary weather satellites with software-defined radio. It covers the extra effort needed to receive GOES data.

A short video accompanying the CVPR 2018 paper Learning to See in the Dark. It shows a neural network producing sharp images from very low-light raw sensor data, compared against denoising approaches.

A one-minute scene from the film Enemy of the State showing absurdly implausible image enhancement, with freezing, rotating, zooming and focusing on a video.

A short Harris Corporation (L3Harris) promotional video showing wide-area airborne motion imagery, a sensor system for persistent real-time aerial surveillance of large areas.

A step-by-step tutorial on making a Harry Potter by Balenciaga style AI video, using tools such as ChatGPT, Midjourney and Eleven Labs for script, images and voices.

Biologist Michael Levin explains the bioelectric layer that coordinates cells to build organs and bodies, showing footage of two-headed worms and introducing xenobots. He discusses implications for medicine and the nature of life.

GDC 2019 session where Insomniac's David Santiago describes the procedural systems used to build Manhattan for Marvel's Spider-Man. It covers the open-world pipeline and how each system was designed to support iteration and dependencies.

A SIGGRAPH Asia 2013 research demo of 3-Sweep, a tool for extracting editable 3D objects from a single photo using a few user strokes. It predates modern AI image tools.

Scott Galloway's TED talk uses data to argue that young Americans are financially worse off than earlier generations, calling it a great intergenerational theft. He covers root causes and what could change it.

Veritasium visits the US Navy's Crane facility to test top night vision goggles. It explains how image intensifier tubes and thermal or digital systems work and compares the generations of the technology.

Neurologist Dr. Matthew Phillips talks at Low Carb Gold Coast 2022 about fasting and ketogenic diets as therapies for cancer and neurodegenerative disease. He focuses on mitochondrial dysfunction and brain energy metabolism.

A short side-by-side demo of a large image loading over a slow connection in JPEG, progressive mozjpeg, JPEG XL and AVIF. It shows how each codec renders partial data.

OpenAI's livestream demo of GPT-4 with Greg Brockman, showing its capabilities and limitations. Highlights include writing code, turning a hand-drawn sketch into a website, and a tax-question example.

A short demo video for NVIDIA's StyleGAN paper, which proposes a style-based generator for GANs. It shows face synthesis with style mixing and scale-specific control over attributes like pose and freckles.

Lord David Willetts argues at the Royal Institution that the post-war baby boomers gained wealth and security at the expense of younger generations. He draws on his book The Pinch, covering housing, wealth and social policy in the UK.

Moxie Marlinspike speaks at Next Generation Threats 2014 about the challenges of encrypted communication and how Signal addresses them. He also draws on American action movies as narrative for secure communications.

Benn Jordan's video about storing a PNG image in a living bird, a starling that learns to reproduce encoded sounds. It mixes ornithology, audio engineering, and data encoding.

Peter Norvig, then Director of Research at Google, talks at Startup School 2008 about leveraging large amounts of data and about technical challenges in Google projects such as image search. A central idea is that data can beat hand-written programming.

Jessie Frazelle's DockerCon SF 2015 talk on running Docker containers for desktop applications, with fun container hacks and images. It shows how far containers can be pushed beyond servers.

Robert Moss's JuliaCon 2015 talk describes using Julia as a specification language for ACAS X, the next-generation airborne collision avoidance system that succeeds TCAS.

Associate Professor Simon Michaux presents estimates of the metals needed to build one generation of renewable technology to replace fossil fuels. He argues current production and reserves fall far short, with copper a key shortfall.

A one-minute clip from a CSI episode featuring the trope of zooming and enhancing low-resolution images. The uploader says it was the last CSI episode they watched.

A two-minute supercut of film and TV characters ordering a computer to 'enhance' a blurry image into a perfectly sharp one. It is a remaster of an earlier 2009 version.

A spectrogram analysis of Aphex Twin's track commonly called [Equation] from Windowlicker, rendered from a lossless version. At about 5:30 the spectrogram reveals an image of Richard D. James's face.

A King of the Hill clip in which Hank-style character rants about saving images as PNG instead of JPEG after exporting from Windows Paint.

A two-minute compilation of TV and film scenes where investigators say 'enhance' and a blurry image becomes sharp. It mocks the trope.

A video presenting an Intel research paper on enhancing the photorealism of synthetic images. A convolutional network uses rendering intermediates, shown on GTA V footage that comes out looking like real street scenes.

A short demo of interactive AI live painting in Krita using the Stable Diffusion plugin, where canvas changes update the generated image immediately. It uses an LCM sampler for speed and needs a high-end GPU for the interactive feel.

Catherine West's RustConf 2018 closing keynote on building a game in Rust and organizing a large codebase. It builds up an entity component system and generational indices step by step.

A full upload of Alan Kay's 1987 talk, with demos of several Smalltalk-era software systems and ideas about visual, kinesthetic and symbolic reasoning. It includes a Smalltalk program written by a 12-year-old and footage of the Rand tablet.