A preprint of our new paper "No Longer Trending on Artstation: Prompt Analysis of Generative AI Art" is available on @arxiv. We analysed over 3M prompts from users of Stable Diffusion and Midjourney and the images generated: arxiv.org/abs/2401.14425
ChatGPT's competitor from Google is taking the internet by storm.
It's called Bard and is connected in real time to the internet.
Here are 10 useful prompts that can be used on Bard (but not on ChatGPT):
One last thing- contrary to popular belief, this thread was NOT free.
I spent all week curating this, so I'm hoping you honor the gentlemen's agreement:
1. Follow me @rowancheung for more
2. Like + Retweet the tweet below to share 🤝 teapaw.org/rowancheung/status/165…
ChatGPT saves me hours of work every day.
But you should write the good prompts.
Here’s a list of insanely useful prompts (I can’t live without):
SensiLab will be hosting 2 new workshops in Prato, Italy this year. The first is on co-creative AI (26-30 June). The second is on Practice-Based research (3-7 July). Attendance is free, but places are limited. To register: sensilab.monash.edu/news-eve… and sensilab.monash.edu/news-eve…
Last week we presented a new research paper that addresses the question: "is writing prompts really making art?" at the @EvostarConf We explore creative and ethical issues for software made by @midjourney, @OpenAI and @StabilityAI. Preprint here: arxiv.org/abs/2301.13049
We’re developing a new tool to help distinguish between AI-written and human-written text. We’re releasing an initial version to collect feedback and hope to share improved methods in the future. openai.com/blog/new-ai-class…
En @icesi nos enorgullece que el prestigioso @MIT @techreview, en su edición de las 10 tecnologías más influyentes del año, cite a nuestra graduada Teresa Llano profesora @MonashUni @MonashInfotech y experta en la automatización de los aspectos creativos del razonamiento humano.
AI models that generate stunning imagery from simple phrases are evolving into powerful creative and commercial tools. That's why our reporters and editors named text-to-image AI as one of this year's 10 Breakthrough Technologies. trib.al/V2iQYpA
ChatGPT is reinvigorating the debate over whether human creators need to cite every work they've ever experienced in every work they produce.
(Not possible. But open datasets with similarity search are what this is already 😂)
¡Ya disponible! "Inteligencia Artificial Feminista: Hacia una agenda de investigación en América Latina y el Caribe" Son más de 50 autoras entre participantes de la red f<a+i>r e invitadas.💖archive.org/details/intelige… #iafeminista
Congratulations to Dr Nina Rajcic (@ninarjcc) who has been awarded her PhD for the thesis titled "Posthuman Rituals"
You can find out more about Nina's amazing work here: sensilab.monash.edu/research…
It’s not GUI, it’s TUI! This is work on ‘Tangible User Interfaces’ @TheMediaLab that will allow people to interact with bits in ways other than just through screens, coupling the ‘dual worlds of bits and atoms’. Pretty freaking cool tangible.media.mit.edu/ – at Cambridge, MA
Are you interested in helping to develop new explainable creative AI systems? Like to work with us at SensiLab? We have a 3 year PhD scholarship available for a suitably qualified researcher interested in explainable artificial creativity! Details at: supervisorconnect.it.monash.…
Given the speed of #stablediffusion 's generation, automated image/prompt curation is becoming a necessity.
I've been using @RiversHaveWings aesthetics rating model to build an evolutionary algorithm that evolves a random prompt population to become more aesthetic. 1/x
Design@Sydney is hiring! Are you interested in a research+teaching Lecturer/Senior Lecturer position in HCI and/or Interaction Design? To all my co-creativity and human-centred creative AI peeps: that definitely includes you!
higheredjobs.com/institution…
Octopus Attack!
My third #cyberpunk Giger-Train piece using #StableDiffusion. This one deserves full screen for all the gory detail... Never would have thought I could do something like this with just prompts and code. @EMostaque @StabilityAI #GenerativeArt #AIArt #CreativeAI
Received the hardcopy of the book of X, the physical copy is beautiful bookof.xcoax.org
A great school holiday activity, Take CTRL offers free workshops on creating with #code - no experience needed!
From using bumble-B units to address a social good issue to making art with @sensilab_monash's DrawBots, it's a day that can't be missed: ow.ly/QWTS50KpXhk
Delighted to announce the public open source release of #StableDiffusion!
Please see our release post and retweet! stability.ai/blog/stable-dif…
Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity
Been experimenting with fine-tuning #stablediffusion to use CLIP image embedding as the conditioning instead of a text prompt. This allows you do do the dalle2 like "image variations"




























