Emberblend

I make donationware content to use in your projects!

[Emberblend @emberblend]

@NVIDIAGeForce #RTXON

[Emberblend @emberblend]

@NVIDIAStudio #GeForceRTX50

[Emberblend @emberblend]

@NVIDIAGeForce #GeForceRTX50

[Emberblend @emberblend]

@NVIDIAGeForce #GeForceRTX50

[Emberblend @emberblend]

@NVIDIAStudio #GeForceRTX50

[Cristóbal Valenzuela @c_valenzuelab]

One of the most fascinating aspects of this model is its ability to unlock hidden creative potential. People are discovering new modes of imagination they never knew they possessed. It's like watching someone learn a new language in real-time. Tapping into parts of their minds that have lain dormant, exercising mental muscles they never knew existed. They are thinking abstractly or making unusual connections between concepts. Real-time cognitive flexibility. And there is joy and wonder on their faces. A lot of joy. A lot of wonder.

[Andrej Karpathy @karpathy]

Love letter to @obsdmd to which I very happily switched to for my personal notes. My primary interest in Obsidian is not even for note taking specifically, it is that Obsidian is around the state of the art of a philosophy of software and what it could be.

- Your notes are simple plain-text markdown files stored locally on your computer. Obsidian is just UI/UX sugar of pretty rendering and editing files.
- Extensive plugins ecosystem and very high composability with any other tools you wish to use because again it's all just plain-text files on your disk.
- For a fee to cover server costs, you can also Sync (with end-to-end encryption) and/or Publish your files. Or you can use anything else e.g. GitHub, it's just files go nuts.
- There are no attempts to "lock you in", actually as far as I can tell Obsidian is completely free of any user-hostile dark patterns.

For some more depth, I recommend the following writing from CEO @kepano:
- "File over app" https://t.co/SigWj8uCrf . If you want to create digital artifacts that last, they must be files you can control, in formats that are easy to retrieve and read. Accept that all software is ephemeral, and give people ownership over their data.
- "100% user-supported" https://t.co/2qDJXub7cs . On incentives alignment.
- "Quality software deserves your hard‑earned cash" https://t.co/qfNjSEwbLf

TLDR: This is what software could be: private, secure, delightful, free of dark patterns, fully aligned with the user, where you retain full control and ownership of your data in simple, universal formats, and where tools can be extended and composed.

[Emad @EMostaque]

This is the first in a series of video (& other!) models we are releasing - all modalities will be powered by Stability 🦾

From external testing last week this is already the best img-to-video model out there & better coming.. 👀

Fantastic work by team👏🏾

Please RT & AMA! 👇🏾

[Stability AI @StabilityAI]

Today, we are releasing Stable Video Diffusion, our first foundation model for generative AI video based on the image model, @StableDiffusion. As part of this research preview, the code, weights, and research paper are now available.

Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface.

To access the model & sign up for our waitlist, visit our website here: https://t.co/IcuPJr45S9

[Emad @EMostaque]

State of AI

[Emberblend @emberblend]

@MoveAI_ To make emotive animations!

[Emberblend @emberblend]

@hessejt @icreatelife The aesthetics of generated pixels are much more refined, flexible and elegant than rendered pixels with less manual work beforehand tho!

[Emberblend @emberblend]

@PLAYFUL_FUTBOL @nickfloats I anticipate AI will help with that too and usher in an era of middle class creators.

[Emberblend @emberblend]

@KeyTryer Just want to note that i had this experience far more pre-Elon - mostly on politically spicy tweets though.

[Dy Mokomi @dymokomi]

Once people internalize how their brain and creativity works, the heated discussion about AI vs non-AI will fade int fringes of the Internet. In a way, the reaction we see is deeply rooted of feeling that we’re somehow special, that there is no algorithm running in our brains. We do need some advancements in neuroscience for that to happen, but there is plenty of published research from early theories by Hubel and Wiesel on our visual system that inspired CNNs to current cognition theory by Jeff Hawkins from Numenta - A Thousand Brain theory, which I can’t help but see how similar it is to LLMs and diffusion models.

[Emberblend @emberblend]

@Swiftbleu @Kerama3dDesigns @EMostaque @Gagurum Is it a little echo chamber if it’s the majority of society tho? That’s what you don’t get - this is an open debate and not everyone agrees with you. It’s not cut and dried no matter the denigrating rhetoric you employ.

[Emberblend @emberblend]

@johnowhitaker 3 things to try! Img2img depth model, pix2pix & runway ML new video model! I have to work out this workflow too so it’s on my mind.

[Emberblend @emberblend]

@venustheory My honest take is that idea/learning compression through novel presentation techniques is one of the only underexploited values in a sea of talking head YouTubers.

[Claire Silver 🌸 @ClaireSilver]

🚨AI Art Contest 3🚨

Prize:

1st: 3ETH
2nd: 1.5ETH
3rd: 1 ETH
4th/5th: .5 each

& gallery exhibition.

Rules: Max 2 entries. Post here. Ends 1/28/23.

Theme: “Rebuttal:” make a piece that responds to an argument against AI art with beauty, skill, or message. Don’t be hateful.👇

[Claire Silver 🌸 @ClaireSilver]

stable diffusion 2.1 is pushing the ceiling on the uncanny valley #AIart