View allAll Photos Tagged generating
Generated with actionscript, colorized with Photoshop. It took a while to get the right feeling. I'm very happy with the results.
Orginal render size:4800x4800
Available for print. contact me: mark.knol.at.gmail.com
AI artwork generated with Stable Diffusion AI v1.4
Prompt: "abstract art of a beautiful portrait, solid shapes, neotokyo colors, muted colors, stylized visual effects, geometric, depth of field, tilt shift, fil "
Seed: 7474672
CFG usually either 7, or 14
Upscaled with Topaz Gigapixel AI:
- Upscale: 2x
- Mode: Standard
- De-noising: 0
- Blur Reduction: 20
- Face recovery: 10
My Workflow:
- Generate hundreds of 10-20 step "rough draft" images in Google Colab
- Grab the seeds of the good-ish ones
- Rerun in Google Colab with 50-100 steps using the seeds
- Send the good images to Gigapixel AI, export with Standard Mode settings
- Finally, send them through Sharpen AI, often with "Too soft - Normal" and 30-70 added grain. This step isn't that crucial, but it does help a tiny bit.
- Post to flikr with JS scripts to automate this description :)
- Probably about 1%-5% of AI generations get posted to Flickr. It depends a lot on the prompt, different prompts run into different issues. Bust portraits tend to be more successful since hands, arms, and legs almost always come out wrong.
Start creating right away with the official Stable Diffusion web UI: beta.dreamstudio.ai/
You get 200 free credits. Alternatively, find a Google Colab to make images at a cheaper rate. My personal one is too personalized to publicly share.
Join the Stable Diffusion community on Discord: discord.gg/stablediffusion
Almost all generations use v1.4 Stable Diffusion. However, a couple anime-related images may instead use the anime-trained Stable Diffusion model, "Waifu Diffusion".
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
The NIPSCO Michigan City Generating Station photographed from the draw bridge over Trail Creek. Longbowsnyper and I toured the Indiana Dunes National Lakeshore from Michigan City to Portage, IN on our fixed gear bikes. We each had totally manual 35mm cameras with 50 mm lenses and no light meters. The combination of fixed gear bikes and manual film cameras made for a fine Vintage day.
Photographed on Kodak Tri-X 400 film using a Nikon F with a Yellow Wratten 8 filter and polarizer on a Nikkor 50mm f/2 lens. Exposure was by Sunny 16 -2 stops to account for the filters. The camera was at f/5.6 for this shot for better depth of field control.
A series of AI-generated pictures of a jungle pilot taking a break.
To be continued.
Pictures made with Midjourney.
I'm always happy to accept invites to groups as long as I can see their content. Should I see "this group is not available to you", my pictures won't be made available to that group. Thanks for your understanding.
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
The Mesh Files
A folding-experiment-series of user generated and computer aided mesh structures with semi flexible material. An originally flat and planar surface is bent as a result of force based deformation.
Resulting folds in the presented artifacts are formed in response to temporarily applied compressive stresses to different sections of the surface. Due to the non-fluid characteristics of the surface, it is not able to deform like an ideal fluid but instead bucks and forms folds.
A two dimensional mesh grid is generated by a custom made software. the amount of cells per gird is based on the amount of cells when folding paper xy-times into half - that is 2 to the power of x for all columns and 2 to the power of y for all rows. Each rectangular cell is divided into 2 triangles by adding a diagonal edge. The mesh now consists of n-amount of edges and m-amount of vertices.
The software allows the user to displace individual vertices of the mesh based on a given set of rules. The vertices located at the boundaries of the mesh can only be moved along its corresponding axis. This restriction allows the mesh to maintain it's original rectangular shape.
Foam board 3mm white is used as source material. Foam board consists of three layers. Enclose the core foam layer is enclosed by 2 layers of paper. The computer generated mesh is projected onto each foam board. During the process of making, the foam core and one paper layer is cut with a pen-knife for every edge of the applied mesh.
Waukegan Electric Generating plant owned by Edison International and located at 401E. Greenwood Avenue in Waukegan, Illinois.
Right nearby is Lake Michigan, Waukegan beach recreation area, downtown Waukegan, parks, schools, playgrounds and neighborhoods.
Demographics of the three mile area near the plant: average income $16,197; population of 67,776 people; 72.1% Latino; 18.7% African American.
Emissions as of 2006: Carbon Dioxide 4,829,238 tons; SO2 11,815 tons; mercury 4,940 tons.
Health costs in human terms every year from this plant alone: 34 deaths, 54 heart attacks, 570 asthma attacks, 25 hospital admissions, 25 chronic bronchitis episodes, and 35 ER admissions for asthma attacks.
The company says that "it believes it is demonstrating environmental responsibility, and that it is being targeted unfairly.
Information taken from sourcewatch.org.
Generate London 2015, the conference for web designers, presented by net magazine and Creative Bloq.
17 and 18 September 2015 at the Grand Connaught Rooms in London.
Various Ai generated images of Nancy Pelosi. These images are licensed CC0 and entered into the public domain for anyone to use for any reason.