Daniel (@danielbln) 's Twitter Profile
Daniel

@danielbln

systems engineering and AI.
berlin.

ID: 16282216

calendar_today14-09-2008 12:04:14

227 Tweet

272 Followers

48 Following

Guy Parsons (@guyp) 's Twitter Profile Photo

So maybe you're familiar with the weird world of DALL·E, but how much do you know about #Midjourney, the OTHER super-duper text-to-image AI? Well, between you and me, it's gotten REALLY GOOD recently – here are some stunning examples that show why you should give it a whirl 👇🧵

fabian (@fabianstelzer) 's Twitter Profile Photo

DALL-E 2 vs Midjourney vs StableDiffusion mega thread: photography, illustration, painters, abstract these image synths are like instruments - it's amazing we'll get so many of them, each with a unique "sound" 🤯 rules: same prompt, 1:1 aspect ratio, no living artists

DALL-E 2 vs Midjourney vs StableDiffusion mega thread: photography, illustration, painters, abstract

these image synths are like instruments - it's amazing we'll get so many of them, each with a unique "sound" 🤯

rules: same prompt, 1:1 aspect ratio, no living artists
Emad (@emostaque) 's Twitter Profile Photo

Delighted to announce the public open source release of #StableDiffusion! Please see our release post and retweet! stability.ai/blog/stable-di… Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity

Remi (@remi_molettee) 's Twitter Profile Photo

Testing #stablediffusion notebook by deforum I used the init image. It’s amazing at times how some of the images in the video have been turned into cartoon #AIart #deforum

Daniel (@danielbln) 's Twitter Profile Photo

ChatGPT is wonderful, but it needs a cancel button like the GPT playground. I often can tell after a sentence or two that this is not what I want, but I gotta let it ramble on until the end.

Daniel (@danielbln) 's Twitter Profile Photo

Overwhelmed by all the AI news coming out? I try to condense all the important bits of the week down to a 5 minute read every Tuesday, so you don't burn out with all the new stuff coming out left and right. Check it out if you feel like it: thegenerativeedge.substack.com

Daniel (@danielbln) 's Twitter Profile Photo

I wonder if you could train an adversarial llm on the prompts of jailbreakchat.com, possibly creating a model that could jailbreak various other models, turning them into mildly adversarial models themselves :thinking_face: