12 Photos and videos
Tomas retweeted
7 Feb 2023
Fake Satellite Imagery
This episode is all about using AI to generate satellite imagery using something called generative adversarial networks ( GANs ).
mapscaping.com/podcast/fake-…
Can you spot the fake image?
14
29
209
42,793
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
significantly improves over previous GANs and outperforms distilled diffusion models in terms of sample quality and speed
abs: arxiv.org/abs/2301.09515
project page: sites.google.com/view/styleg…
8
32
592
85,954
Riffusion, real-time music generation with stable diffusion
@huggingface model: huggingface.co/riffusion/rif…
project page: riffusion.com/about
53
578
2,415
Tomas retweeted
24 Nov 2022
We are excited to announce the release of Stable Diffusion Version 2!
Stable Diffusion V1 changed the nature of open source AI & spawned hundreds of other innovations all over the world. We hope V2 also provides many new possibilities!
Link → stability.ai/blog/stable-dif…
130
1,793
7,735
We are launching a new arXivLabs collaboration with @HuggingFace to make demos related to papers in cs, stats, and eess directly accessible from arXiv!
20
396
2,505
Tomas retweeted
15 Nov 2022
90 Days of Diffusion
90 🤯 AI Advances 👇
77
662
2,653
Tomas retweeted
7 Nov 2022
I've trained a latent diffusion upscaler for the Stable Diffusion autoencoder (and anything you feel like feeding into it if you can tolerate a little artifacts) in collaboration with @stabilityai. Try the Colab written by @nshepperd1 here: colab.research.google.com/dr…
15
102
520
Tomas retweeted
26 Oct 2022
Glad to share our #WACV2023 paper with @jormalaaksonen @Xelfor @heikkiarponen @NotACyborgYet @CSAalto!
Problem: Unaligned vision(V)-language(L) pre-training. Idea: Generate some imaginary V from L, then L can interact with its imaginary friends 😃
arxiv.org/abs/2210.13591
2
3
Tomas retweeted
30 Aug 2022
1 week of Stable Diffusion
A creative explosion is unfolding with Stable Diffusion,s showing the power of open source as state of the art!
We curated 23 applications this week: new features, workflow integrations, UIs; run on Win, CPU, AMD, M1 and more! multimodal.art/news/1-week-o…
8
137
595
Tomas retweeted
13 Aug 2022
We took a representative set of 5.6 billion images from the internet, filtered out weird and low quality stuff to 2 billion, 100 terabytes, and squished it to a 2 Gb file we are making available for anyone to use versus monopolising it.
11
24
282
Tomas retweeted
1 Jul 2022
A colleague of mine generated these Dall-E 2 remote sensing synthetic images, they are pretty convincing.
3
6
52
Most machine learning libraries haven't been designed to work with geospatial data. #TorchGeo, a PyTorch domain library, is set to change this by monitoring some of the world’s greatest challenges, like natural disasters and climate change.
Read more: bit.ly/3tT6Mw7
72
336
CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
abs: arxiv.org/abs/2204.14217
CogView2, shows very competitive generation compared to concurrent state-of-the-art DALLE-2, and naturally supports interactive text-guided editing on images.
13
135
754
ARF: Artistic Radiance Fields
abs: arxiv.org/abs/2206.06360
project page: cs.cornell.edu/projects/arf/
github: github.com/Kai-46/ARF-svox2
create high-quality artistic 3D content by transferring the style of an exemplar image, such as a painting or sketch, to NeRF and its variants
2
126
508
Tomas retweeted
7 Jun 2022
🎉 Happy to share a blog @krasul and I have been working on: the Annotated Diffusion Model.
We implement and train Jonathan Ho et al's DDPM (that forms the base of today's DALL-E 2 and ImageGen) step by step in PyTorch: huggingface.co/blog/annotate…
9
170
845
“Finish the cat drawing” viral meme tweet has replies with all sorts of nice, creative ‘out of the box’ thinking.
I use #Dalle’s inpainting function to do this task, and was impressed at what it can do. Here is the output using the prompt “cats”
🧵An entire thread of results 🐈
This tweet is unavailable
7
264
1,249
Tomas retweeted
27 May 2022
Following Imagen example, I plotted the Pareto CLIP score vs FID over conditioning guidance scales on dalle-mega.
We can notice a few interesting things.
1
2
35
Tomas retweeted
22 May 2022
Let's play a game.
Two cat photos, one is real and the other is a fake generated by DALL-E. Can you figure out which which?
Round 1:
46
30
192