Ex-Google Brain / DeepMind meetup in London
@hardmaru
-
Generating Kanji Images from English Text
By
–
A related experiment, generating “Kanji” images from English text:
-
Effective Concepts for Text-to-Image Models and Latent Space Exploration
By
–
“Tardigrade” works really well on most text-to-image models. There are so many images of them. Other concepts that work well involve insects, animals, plants. Food (pizza, noodles). Historical events (WW2). Medical (X-rays). The latent space is full of exploration opportunities.
-
Critique of Stable Diffusion Community’s Shift Toward Complex Objectifying Prompts
By
–
Sorry… I meant to poke at the SD community with this example that was trending, as a sort of ‘backward progress’ of the state of text-to-image community. We went from “elegant simplicity of creative concept art” (left) → “needlessly complex prompts objectifying women” (right).
-
Neural Networks Enhance Character Learning with Visual Mnemonics
By
–
Check out this 2021 experiment by @azlenelza where characters were augmented with visual mnemonics with the help of neural networks, to make them easier to learn:
-
Duchamp’s Fountain Reimagined as a Futuristic Space Colony
By
–
Duchamp's Fountain (1917) as a Space Colony. #StableDiffusion2 #AIart
-
Duchamp’s Fountain Reimagined as Space Age Architecture via AI
By
–
Duchamp's Fountain (1917) transformed into Space Age architecture. Just as Duchamp's urinal attracted much controversy in 1917, and went on to change the art world, Generative AI will become an art form, and it will change art forever. #StableDiffusion2 #AIart
-
She3PO: Creative AI Art Generation with Stable Diffusion
By
–
She3PO #StableDiffusion #AIart (
https://
redd.it/zums56)
