Latest Posts
6-hour Bicycle Tour of West Oakland
Reading Time: 2 minutes I’m moving to Oakland this week. I’m also working with a startup that’s building a marketplace for travelers to connect with “localites”, experts in the area they are visiting. To get a feel for the value of a locality, I put together an itinerary that I would take my friends on to get a feel … Read more
Scrolling Ticker Ring
Reading Time: < 1 minute The scrolling ticker substrate is a ring suspended from the top of the hyperboloid tower. The ring will be made up of 3 6″ x 16 ft. sections of 1/8″ Masonite. Each section is made up of four pieces of 6″ x 8 ft. Masonite lapped together and secured by sets of 4 small bots … Read more
Platform
Reading Time: < 1 minute Midway up the structure, we need to have a platform to support the power systems. This platform can also stiffen the structure serving transfer tension and compression forces around the helix. I wanted it to be able to support several hundred lbs. of weight that a person and a generator might add up to. At … Read more
Structure – Bamboo poles out, lodge poles in
Reading Time: 2 minutes Our first design for the structure called for 2″ diameter bamboo poles arranged in a helix pattern to form a 14 ft. hyperboloid tower. Each pole was going to be made up of two 8ft. pieces of bamboo cane coupled by using a two-foot 1″ round dowel inserted parallel through the middle of the cane. … Read more
AI-powered Wardrobe: Wardobe-ai.com
Reading Time: 7 minutes I tried out a new beta of an AI-powered wardrobe generator. It is all it's cracked up to be.
Custom Stable Diffusion Model with Two Tokens
Reading Time: 10 minutes I had put together a list of iconic couples, and my goal was to come up with prompts and processes to get good images where our likenesses were substituted into the scene. One significant departure from my previous trials is that I have started incorporating negative prompts into the renderings.
AI Generated Portraits of Two People
Reading Time: 8 minutes My instagram feed is full of AI generated self-portraits. Often surprising and evocative, a passel of sites have quickly spun apps which let people stylize a headshot. More figurative images seem to possess the same sensibility and style as those of well-known artists. I have been doing a deeper dive into the world of generative art. This is my four experiment . Unlike the online apps, which stylize a single image, I have diving deeply into Stable Diffusion to create a model that can generate images of multiple specific people in a wide range of scenes.