Hades is our first game with a big fully-voiced cast of char…
Hades is our first game with a big fully-voiced cast of characters! Our voice cast includes actors we’ve loved working with for years, plus some incredible talent who joined us to help bring our characters to life. Here’s a quick hello from everybody! (Mi
Month: September 2022
Twitterfav archive 09/12/2022
Oh and we also have img2img if you don’t…
@simonw Oh and we also have img2img if you don’t want to set up on your own computer! https://t.co/YieSeWmswG (“init_image”)
A stunning cloudburst over Lake Millstatt, Austria Captured…
A stunning cloudburst over Lake Millstatt, Austria
Captured by Peter Maier https://t.co/aotRue5Q6y
Twitterfav archive 09/11/2022
How To Use To Create A Traditional Ill…
How To Use #DreamStudio #StableDiffusion To Create A Traditional Illustration.
(A micro micro micro documentary with an all-caps title to make it look impressive)
Let’s start with the finished illustration (you’ll want to zoom in on it, so click and rea
With img2img, I can help bring my 4yr o…
With #stablediffusion img2img, I can help bring my 4yr old’s sketches to life.
Baby and daddy ice cream robot monsters having a fun day at the beach.
The first magazine about AI made with AI “236” first issue !…
The first magazine about AI made with AI “236” first issue ! https://t.co/ABOQAAhVQm
“Voyage through Time”is my first artpiece using and I am b…
“Voyage through Time”
is my first artpiece using #stablediffusion and I am blown away with the possibilities…
We’re crossing a threshold where generative AI is no longer just about novel aesthetics, but evolving into an amazing tool to build powerful,
Real World Power/Sex/Money Utility Lost …
Real World Power/Sex/Money Utility Lost to Virtual Entertainment in Social Design Because of Measurability, if you want to be sad about it be sad as a sign of human disempowerment in the real world… https://t.co/8VvSKwaTgD
The coming fall of the Kardashians in context of how enterta…
The coming fall of the Kardashians in context of how entertainment is evolving… (aka why they are so pissed about tiktok) https://t.co/wtYrvxbS35
Twitterfav archive 09/10/2022
TL;DR – 10 AI websites you probably didn…
TL;DR – 10 AI websites you probably didn’t know existed:
• #1 Magic Eraser
• #2 Craiyon
• #3 Rytr
• #4 Thing Translator
• #5 Autodraw
• #6 Fontjoy
• #7 Talk to Book
• #8 This Person Does Not Exist
• #9 Namelix
• #10 Let’s Enhance
10 mind-blowing AI websites you probably didn’t know existed…
10 mind-blowing AI websites you probably didn’t know existed:
This is the future of digital interior design https://t.co/Q…
This is the future of digital interior design https://t.co/Q4HFap6Hdr
Every time I join a new team, it’s the s…
Every time I join a new team, it’s the same conversation https://t.co/tBVJBb4K1J
Twitterfav archive 09/09/2022
Satya Nadella belongs in the CEO hall of…
Satya Nadella belongs in the CEO hall of fame. I’d say he edges out Steve Jobs simply because he turned around Microsoft without the benefit of the clout that comes from being the founder. https://t.co/wSge0SHa4L
West Texas storm chaser Laura Rowe captured the picture of a…
West Texas storm chaser Laura Rowe captured the picture of a lifetime, fantastic shot of a mature supercell thunderstorm, illuminated at varying heights from the setting sun. https://t.co/MxHsoG7g9N
Taking Stable Diffusion for a spin on a basic laptop
I’ve been quite intrigued by the recent public releases of Dall-E followed by Stable Diffusion which allow you to generate images from simple text prompts, & had been trying them out on the free online platforms. The main limitation of these is that you are limited to a certain quota for free, and to really try an opensource tool like Stable Diffusion locally, you need to pretty beefy system with a high end GPU.
All that changed when I came across a project on GitHub that lets you run Stable Diffusion on the CPU thanks to Intel’s OpenVINO framework. I promptly took it for a spin on my 4 year old laptop with an Intel quad core 8th gen CPU. The instructions are provided on the GitHub project itself as expected. If you are using Windows like me, you can do the following:
- Install Anaconda which simplifies the Python setup.
- Create a new environment in Anaconda for the project.
- Open the terminal, create a directory for the project & clone the GitHub repository for the project using the
git clone https://github.com/bes-dev/stable_diffusion.openvino.gitcommand with the project web URL.
- Follow the installation instructions on the project page:
- Install the project dependencies using
pip install -r requirements.txt
- Enable Developer Mode in Windows settings which allows the model to be downloaded on first run.
- If you plan to use the web interface also install streamlit drawable canvas using
pip install streamlit-drawable-canvas, as this module dependency seemed to be missing in the documentation & gave me errors on trying to run the web demo.
- Install the project dependencies using
- Run the script as per instructions replacing the prompt if you want (the developer seems to be a GoT/Emilia Clarke fan) –
python demo.py --prompt "Street-art painting of Emilia Clarke in style of Banksy, photorealism"
On my laptop it takes about 8-10 min to generate an image, though a more powerful CPU with more RAM should be able to cut it down to 3-4 min as mentioned in the project page benchmarks. Either way, it is a worthwhile tradeoff to be able to run it locally.
Here are a couple of results from the prompts I ran on my laptop (I chose a couple of the timeless beauties to see what Stable Diffusion has to offer):