Search found 21 matches

by merttoka
Tue Dec 06, 2022 3:21 pm
Forum: Fall 2022
Topic: wk10 - DALLE-2, Final Review Dec 1, 2022
Replies: 6
Views: 4780

Re: wk10 - DALLE-2, Final Review Dec 1, 2022

Last week, I attempted to use Dall-E 2 to generate visual content for the novel Invisible Cities by Italo Calvino . My original idea was to generate one or two images for all 55 imaginary cities described in the book. However, this proved to be an unrealistic goal. First, Calvino's text does not dep...
by merttoka
Mon Dec 05, 2022 11:46 pm
Forum: Fall 2022
Topic: wk07 - Stable Diffusion - 2nd set, Nov. 10, 2022
Replies: 6
Views: 3907

Re: wk07 - Stable Diffusion - 2nd set, Nov. 10, 2022

This week, I tried three extensions of Stable Diffusion: (1) outpainting in an infinite canvas, (2) video creation using camera movement, and (3) material stable diffusion. Outpainting / Infinite Canvas : Similar to the Dall-E2 outpainting interface, this extension has a friendly user interface that...
by merttoka
Mon Dec 05, 2022 11:03 pm
Forum: Fall 2022
Topic: wk06 - Stable Diffusion 1 - Nov 3, 2022
Replies: 6
Views: 4190

Re: wk06 - Stable Diffusion 1 - Nov 3, 2022

This week, I started exploring Stable Diffusion (SD) running locally on my desktop. Setting up such a complicated system on a Windows machine is usually a pain, but the conda environments and hugging face login integrations made this easy. Initially, the first thing I noticed in SD compared to Midjo...
by merttoka
Mon Dec 05, 2022 10:47 pm
Forum: Fall 2022
Topic: wk04 - MidJourney 3rd + Analysis Report
Replies: 6
Views: 3997

Re: wk04 - MidJourney 3rd + Analysis Report

We used Midjourney for the first three weeks of class, and I've noticed certain qualities of the resulting images. Midjourney seems to utilize the whole canvas for placing visual elements. Interestingly, almost none of the images generated by Midjourney has empty compositional space. The empty space...
by merttoka
Thu Oct 20, 2022 11:17 am
Forum: Fall 2022
Topic: wk02 - MidJourney 2nd project
Replies: 6
Views: 3890

Re: wk2 - MidJourney 2nd project

---------------------- You can see these explorations on a Miro board (Week 2) at this link: https://miro.com/app/board/uXjVPQgjXkQ=/?share_link_id=796714658149 ---------------------- To start this week's explorations, I want to share three images I liked. I used a modified version of George's promp...
by merttoka
Mon Oct 10, 2022 1:03 pm
Forum: Fall 2022
Topic: wk01 - MidJourney 01
Replies: 9
Views: 8091

Re: wk1 - MidJourney 1 - 1st Results

---------------------- You can see these explorations on a Miro board (Week 1) at this link: https://miro.com/app/board/uXjVPQgjXkQ=/?share_link_id=796714658149 ---------------------- As a starting point, I wanted to see how Midjourney prompt parameters affect the output of an image. This website wa...
by merttoka
Wed Dec 16, 2020 2:10 am
Forum: Fall 2020
Topic: Report 3: Material-based, Software-based Explorations
Replies: 8
Views: 3921

Re: Report 3: Material-based, Software-based Explorations

This week, I was mostly drawn to the use of noise in art. Like George and many others mentioned throughout the course, Ryoji Ikeda's aesthetics on the organization of data by modulating the order and chaos is amazing to me. He is a genius in composing his pieces. One particular topic we covered in t...
by merttoka
Sat Dec 12, 2020 11:39 am
Forum: Fall 2020
Topic: Report 7: Aesthetic Explorations in AI
Replies: 7
Views: 4009

Re: Report 7: Aesthetic Explorations in AI

Originally intended for problems that are hard to solve using algorithmic methods, artificial intelligence provided a new lens for computer scientists to tackle harder problems with the help of real-world data. It was almost inevitable for these systems to be employed by artists for aesthetic explor...
by merttoka
Sat Dec 12, 2020 8:19 am
Forum: Fall 2020
Topic: Report 5: Generative Art, Computational Aesthetics
Replies: 7
Views: 4564

Re: Report 5: Generative Art, Computational Aesthetics

As Galanter puts it in his canonical publication What is Generative Art? Complexity Theory as a Context for Art Theory , the generative art is an "art practice where the artist uses a system, such as a set of natural language rules, a computer program, a machine, or other procedural invention, which...
by merttoka
Fri Dec 11, 2020 5:34 am
Forum: Fall 2020
Topic: Report 6: Vision & Machine Learning
Replies: 6
Views: 3621

Re: Report 6: Vision & Machine Learning

This week, I appreciated the discussion about human vision and machine learning methods. Interestingly, I recently came across an article that improves the robustness of object detection methods using CNNs by mimicking the visual cortex of human brains. ss.jpg The authors mention that the current ob...