Christopher Pietsch

I have been cooking up a project over the last year and now it is finally ready: Merge your creativity with AI and transform the world around you! ✨Transferscope is a handheld device that lets you capture any object or concept and blend it seamlessly onto any scene.

@micahstubbs or diy ;) hackaday.com/2024/10/10/bui…

@chrispiecom you know you want one x.com/micahstubbs/st…

@fofrAI > go physical: aid-lab.hfg-gmuend.de/articles/trans…

> pick an object and recreate it made out of something unlikely, keep it in context

Some more insights into arafed events.ccc.de/congress/2024/…

Arafed

A powerful way to think about user interfaces is as them being bases of a latent space manifold. There is a nascent niche of interesting experiments exploring these and I will try to curate some of these that came into my notice in this thread.

Almost there: youtube.com/watch?v=PCL9SA…

What will happen when those diffusion models hit our phones and our personal photos are not genuine anymore? "make me look like last summer", "remove grandma from the picture" or "add person x to the group". Also: what crazy compression level will be achieved ?

unStable Mirror is currently on display at the @Kikk_Festival in Namur! come and have some fun with it :) kikk.be/exhibitions/ch…

FLUX that Plays Music paper page: huggingface.co/papers/2409.00… This paper explores a simple extension of diffusion-based rectified flow Transformers for text-to-music generation, termed as FluxMusic. Generally, along with design in advanced Fluxhttps://github.com/black-forest-labs/flux model, we transfers it into a latent VAE space of mel-spectrum. It involves first applying a sequence of independent attention to the double text-music stream, followed by a stacked single music stream for denoised patch prediction. We employ multiple pre-trained text encoders to sufficiently capture caption semantic information as well as inference flexibility. In between, coarse textual information, in conjunction with time step embeddings, is utilized in a modulation mechanism, while fine-grained textual details are concatenated with the music patch sequence as inputs. Through an in-depth study, we demonstrate that rectified flow training with an optimized architecture significantly outperforms established diffusion methods for the text-to-music task, as evidenced by various automatic metrics and human preference evaluations.

@micahstubbs Or it is streaming a 3d scene :) x.com/levelsio/statu…

@chrispiecom x.com/Andercot/statu…

Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)

#EdgeAI 🤖 Check out @chrispiecom's Transferscope! Using generative AI, Raspberry Pi Zero 2, Raspberry Pi Camera Module 3, HyperPixel screen & XIAO RP2040, it captures real-world textures to create unique visuals. No need for complex prompts—just point, capture, and transform! For more details check out our blog in the link below 👇 bit.ly/4djvaeG

"Learning to See: Hello, World!", 2017

@seeedstudio @Raspberry_Pi One with dual M.2 slots :)

😉Better late than never, what kind of @Raspberry_Pi 5 NVME hat do you want? Share your ideas in the comments! #nas #homeserver #mediacenter #AI #ssd #PCIe #LLM #3Dprinting #nvr #robotics

@jonaspelzer Love the seamless transition!

@digikey @makerprojectlab @sparkfun @printablescom @xrpRobots @instructables @3djake_official @MakerIO @DigiKeyEU Thank you for this awesome feature and feedback! Initially I actually build an App to experiment with the generator but then switched to building the device because it added an other layer of joy to the experience. *and fiddling with electronics rocks :)

Ready for the @MakerProjectLab Maker Update? Let's goooo! 👏 🤩: @chrispiecom @sparkfun @printablescom @xrpRobots @instructables @3djake_official, Borge Designs, The Byte Sized Engineer , @Makerio, @DigikeyEU

@seeedstudio @pimoroni @Raspberry_Pi @dfrobotcn This sounds too good to be true :) Will get back to you on this one!

@chrispiecom @pimoroni @Raspberry_Pi @dfrobotcn Thanks for the feedback, Christopher. Just a side note, we do offer customization services for all our hardware products, including #SenseCAPIndicator. Feel free to reach out whenever you're ready to scale up to this super cool project. 😊

I have been cooking up a project over the last year and now it is finally ready: Merge your creativity with AI and transform the world around you! ✨Transferscope is a handheld device that lets you capture any object or concept and blend it seamlessly onto any scene.

@seeedstudio @pimoroni @Raspberry_Pi @dfrobotcn 🙏 At some point I looked at the SenseCAP Indicator D1, but wanted a higher resolution. My dream would be a screen with a cm4 module connector.

@chrispiecom @pimoroni @Raspberry_Pi @dfrobotcn Super cool. Will feature it on our blog SOON!

Breakdown of hardware used for the device: 🖼️ Screen: HyperPixel 4.0 square @pimoroni 🖥️ Computing: Raspberry Pi Zero 2 @Raspberry_Pi 📷 Camera: RPI Camera Module 3 🕹️ I2C - Button: Seeed XIAO RP2040 @seeedstudio 🔋 Battery: 18650 Li-Ion with @dfrobotcn Power Booster

If you want to know more about Transferscope have a look at aid-lab.hfg-gmuend.de/articles/trans… Big thanks for all the help, inspiration and feedback goes out the awesome AI+D Lab Team: @bndktgrs, @saeneas, Rahel Flechtner, Felix Sewing, @alexabruck and Stamatia Galanis

@OpenMoji I call them genOpenmoji now

taking a stroll in openmoji latent space

Circled back to my favourite open source image dataset #OpenMoji. This time I trained #stablediffusion on @OpenMoji to create some new emojis.