2023f


Instructor



MAT255 Techniques, History & Aesthetics of the Computational Photographic Image


George Legrady | http://vislab.mat.ucsb.edu
 

Course materials are protected by US Copyright laws and by University policy. Contents of this course may not be reproduced, distributed, or displayed without my express prior written consent.

Tues-Thurs 1-2:50pm (some lectures may be online) otherwise Lab 2611, 2nd flr, ELings Hall


Course Information
An interdisciplinary course that examines, thorugh case studies, the state of the photographic image, its history, the theoretical, conceptual, and philosophical underpinnings. The course bridges studio arts, engineering, and humanities. This course may be of interest to artists, humanities researchers or programmers as there are three directions to explore:
  1. The aesthetic creative applications, opportunities and constraints,

  2. The computational processes from image processing to machine-learning, and

  3. The social considerations – to what degree can we believe in the image given the considerable software-based processing and autonomous image detail generation we are seeing through machine-learning processes.

The end goal is to investigate the photograph’s transformation through weekly presentations of projects, methods and discussion leading up to the impact of machine-learning on the creative process resulting in computational generated artworks.


Course Workload

Attendance and participation at zoom lectures
Weekly contribution to course journal at Student Forum | Legal agreement
Final presentation pdf documentation of either a research paper OR project


09/28

Course Overview, Apparatus Fundamentals


10/03


10/05



Lab
MidJourney Introduction
Discord Link

MidJourney Controls
MidJourney Variations | Will Wulken Prompt Control Studies

MidJourney Project 1:txt2img

10/10




10/12



Lab
The Image as Statistical Average
Nancy Burson
Jason Salavon
A Kind of Alchemy: The Work of Art in the Age of Artificial Intelligence | AI Post Photography

Diffusion Model
Diffusion Model | Guassian Distribution

MidJourney Project 2:txt2img

10/17









10/19

The Screen as Camera
Point of View | Depth of Field | Lytro

Training Set DataBase
LAOIN5B
Conceptual Captions (CC3M)
YouTube 8M
HaveIbeentrained.com
MOMA: Artist and AI | Trevor Paglen

MidJourney Project 3:img2img

10/24

10/26

Review img&img Projects

MidJourney Project 4: Text-to-Video

10/31


11/02

Stable Diffusion
0.9 | ML Models | HuggingFace | SDiffusion Interface

Stable Diffusion 1: 5+Images | What is An Image?

11/07


11/09

Stable Diffusion
SDXL Stability AI | SDXL v1 |

Stable Diffusion 2: Comparison

11/14


11/16

Stable Diffusion
SD Multiple Features | GitHub: Automatic1111

Meeting / Lab

11/21

11/23

Stable Diffusion 3: Studies

Thanksgiving

11/28


11/30

Final Project Lab
Explorations with GPT-4V | Diffusion Explainer | Levels of AGI

Final project presentation

12/05

12/07

Final Project Lab

Final Report

Final Projects






P. "Rumi" Bhattacharyya

Luis Chavez Carrillo

Colin Dunne

Grace Feng

Bryan Guerra

Autumn Smith

The course introduced MidJourney and Stable Diffusion as txt2img and img2img prompt-based image generators. Topics covered in the course also included examples from the history of photography, conceptual art, artists who have worked with statistical imaging, diffusion models, point-of-view, depth-of-field, links to various AI generative image synthesis. Final projects are student defined, based on topics covered in the course with images generated by either of the two generative image synthesis software.

Mythology of the Post-Colonial

Infectuous Nostalgia

Abstracted Space

Who, What & Where?

A Human Experience

Narrative Building, Understanding, and Visual Cohesion Across Frames

Reference Links
Scientific Image Examples
AI Resistance
Forensic Applications
Other References

Lev Manovich: Artifical Aesthetics: A Critical Guide to AI: Media and Design
Evidence Photos | Tate Article
NightShade/MIT | U Chicago Glaze [arvix paper]
AI Image Detectors
Baldessari/Tom Waits | Roland Barthes, Mythologies