Stable Diffusion is now available as a Keras implementation, thanks to @divamgupta!


Original repo:…

This port has several advantages: (thread) Image
1. It's extremely readable. Go check out the code yourself! It's only about 500 LoC. I recommend this fork I started which makes the code more idiomatic & adds performance improvements (though the code quality of the original was excellent to start with):…
2. It's fast. How much faster? It depends on your hardware (try switching on `jit_compile` to see if you can get a greater speedup that way). Benchmark it on your system and let me know!
3. It works out of the box on M1 MacBooPros GPUs. Just install the proper requirements `requirements_m1.txt` and get going.

(This required no extra work on the repo.)
4. It can do TPU inference out of the box: just get a TPU VM and add a TPU strategy scope to the code. This can yield a dramatic speedup (and cost reduction) when doing large-batch inference.
5. It can also do multi-GPU inference out of the box (same, with a MirroredStrategy scope). It just... works.
6. You can export the underlying 3 Keras models to TFLite and TF.js.

This means that you can create AI art apps that run on the device (in the browser, with local GPU acceleration, or on an Android / iOS device, also with local hardware acceleration). No server costs!
Sounds exciting? Go try it, fork it, hack it. And if you want to learn more about what it looks like to work with Keras and TensorFlow, go read the code:…
Huge thanks to @divamgupta for creating this port! This is top-quality work that will benefit everyone doing creative AI.

I'm always amazed by the velocity of the open-source community 👍

• • •

Missing some Tweet in this thread? You can try to force a refresh

Keep Current with François Chollet

François Chollet Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!


Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @fchollet

Jan 25
AI assistance has a bright future -- applications where humans can guide a search/generation process and correct its output as needed. But keep in mind that's not AI autonomy -- AI agents capable of action on their own in the real world beyond a very narrow scope of automation...
AI autonomy is many orders of magnitude harder, and current techniques are infinitely far from it. They're not even pointing in this general direction.

The good news is, you can produce tons o value with AI assistance -- though that's as much a design problem as a tech problem.
The job of the future is *AI UX designer*: figuring out novel and effective ways for humans to interact with data manifolds. Natural language dialog is just one modality out of many.
Read 5 tweets
Jan 24
If you want to define AGI in terms of outcomes rather than in terms of its function, then "pass this test designed for humans" doesn't cut it. I'd just use the bar set by Sam Altman in 2019: AGI is that which will "capture the light cone of all future value in the universe".
We will know we have AGI when the majority of the world's GDP is being produced by autonomous AI agents.

(And once we get on this trajectory it will be pretty clear, so we'll know much earlier -- it will probably be obvious at 5-10% of global GDP)
You can fake many things, including a Turing test, but you cannot fake economic value created, at least not at scale.
Read 5 tweets
Jan 21
What people don't realize is that this is the default state of housing in a market economy, and it's great for consumers. Turning aging homes into an investment vehicle by artificially constraining supply, the way it's done in the US and many other places, is extremely harmful.
You can achieve the same with any good for which there is enough demand -- cars, professional licenses, etc. Just produce new units at a rate that's 50% that of demand growth and watch prices steadily increase over time.
Satisfying demand growth for housing is relatively straightforward: Make it easy to get permits. Allow mixed use zoning everywhere. Build denser (40 floors) in more attractive areas. Invest in public transportation to increase the surface of those areas. That's the Tokyo model.
Read 7 tweets
Jan 18
It's accurate that can tell a lot about someone from their spouse. But the way it's framed in the post is unhinged, effectively saying "if you have a high status spouse, you see yourself as high status, but if you 'settle' for a low status spouse, you see yourself as low status"
Marriage isn't a status game, and it says a lot about you if you pick your spouse that way.

What you actually want to find out is:

- is their spouse a good person
- do they have a happy / loving relationship with their spouse
- how many times have they been married
The post only gives you one sentence to justify judging people from their spouse and it's literally "it tells you what someone thinks they deserve in life, or what they will settle for". Sad, and echoes the rest of the content -- judgmental and status focused
Read 4 tweets
Jan 18
I rarely make predictions about the future. But I did make one last year, so it's worth fact-checking it. On June 16 I predicted that the market was "not to far from" the year's bottom.

VTI (i.e. the overall stock market) closed at 183.02 that day.
There were exactly 9 days in 2022 with lower closing prices, September 26, 27, 29, 30, and October 7, 10, 11, 12, 14. The absolute lowest close was 179.30, exactly 2.0% below the close for June 16.
I say the prediction qualifies as correct. Didn't nail the absolute bottom for the year, but I did say "not too far from it", and "within 2%" isn't too far.
Read 4 tweets
Jan 16
It's *actual data* time...

TensorFlow & Keras usage is at an all-time high, at >2.5M users. It has increased ~30% yoy.

In the largest developer survey in the world last year (60k respondents), 13% of *all devs* said they used TensorFlow. That's 1.5x more devs than PyTorch.
In the largest 2022 survey of the ML landscape specifically, 57% of ML devs said they used TF. Only 38% said they used PyTorch.

Again, that's 1.5x more devs than PyTorch. This 1.5x ratio is found in virtually all of our metrics.
TensorFlow has 170k stars on GitHub. It's the #3 most starred code repo on there. New stars are growing at a 1.5x faster rate than PyTorch.
Read 10 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!


0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy


3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!