Eyal Gruss (@eyaler) header
Eyal Gruss (@eyaler) profile picture

זורם

Joined May 2009
Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)Photo by Eyal Gruss (@eyaler)
Eyal Gruss retweeted
EndlessDreams: Voice directed real-time video at 1280x1024. A 2+ min video gen'ed directed by my voice in 2min. A crude first start. Don't confuse smooth 60 sec vids that take hours to do. This is RT exploration of gems hidden in the latent space. This is only the beginning.
31
88
45
391
56,053
Eyal Gruss retweeted
TL;DR: We use SDS from text-to-video models to animate vector-graphics sketches! Please check our project page for more details, and more penguins: livesketch.github.io/
27
234
36
1,119
174,536
Eyal Gruss retweeted
this is mind-blowing. running SDXL in real-time with LCM-LoRA.
23
155
30
1,220
156,491
my language model is not like yours
16
68
6
608
78,059
Laura Cellier, présentatrice d'i24NEWS en anglais, dénonce la polémique sur l'information relatant les 40 bébés assassinés par le Hamas i24news.tv/fr
13
53
9
99
13,710
Eyal Gruss retweeted
Pearl with a Girl Earring. #dalle3 #midjourney #photoshop #vermeer
49
190
27
1,917
250,210
If Midjourney existed before Picasso, would we be able to prompt it for a cubist portrait? And if so, would we recognize its beauty without recognizing Picasso’s genius first?
2
1
7
892
Eyal Gruss retweeted
Generated a (B movie themed) video clip for this random royalty free sound track I liked: storyblocks.com/audio/stock/… Also in this case, many 2 second snippets were generated with text2video and edited together with Videoleap into this "Music clip"
12
8
1
57
6,771
פיד קריאייטיב! שתפו היום עלה הקורס החדש שלי, שבו תוכלו ללמוד איך להשתמש במחוללי הדימויים החדשים. ממתחילים גמורים עד לרמה המקצועית הגבוהה ביותר. דאלי, סטייבל, מידג'ורני, יהפכו את הסקיצות, המצגות, העיצובים, הפוסטים שלכם לפלא. זה ממכר ביותר. הרשמו עכשיו! rotm.co.il/
3
10
Took a face made in #stablediffusion driven by a video of a #metahuman in #UnrealEngine5 and animated it using Thin-Plate Spline Motion Model & GFPGAN for face fix/upscale. Breakdown follows:1/9 #aiart #ai #aiArtist #MachineLearning #deeplearning #aiartcommunity #aivideo #aifilm
128
878
137
4,904
AI Oil Painting, described by one AI and imaged by another, curated and painted by humans. Show opening @vrhamfestival Venice 9/1 and @GazelliArtHouse London 9/8 gazelliarthouse.com/exhibiti… Made with #gpt3 #dalle2 and #midjourney by @OpenAI and @midjourney #AIart
1
5
1
25
Excited to announce that #stablediffusion is coming to Artbreeder, bringing together the power of @StabilityAI’s model with the playfulness and control of Collage!
48
161
42
815
Eyal Gruss retweeted
W.I.P. collage tool for stable diffusion
101
1,213
220
4,917
Using dall-e 2 to manifest what’s not real. Another test combining dalle stop motion with moving video. This time blending ai generated objects with a real object #dalle #openai #experiment #dalle2 #aiart
37
248
38
1,710
We’re hard at work on a new way to make generative art, and are excited to share our first prototype! Create any scene you can imagine with a simple collage and a prompt. Try it out! collage.artbreeder.com/
141
2,026
365
10,889
Eyal Gruss retweeted
DeepMind’s Flamingo understanding of a picture with natural language processing.
4
1
17
Evra project mixes some ancient Kabbalah magic with modern machine learning. What are these letters, and what does this text, inscribed on a clay tablet, say? Let me tell you the story of Evra, a collaboration with @eyaler 👇 #MachineLearning #ml #ai #generativeart #kabbalah
1
2
8
Thrilled to announce my solo exhibition "Latent Spaces" opening this Tuesday in Jerusalem! Curated by Sara Kopelman and Noa Maccabi, I'll be showing generative art works from the last two years, process sketches, + a brand new one I'll be telling you about in the coming days.
1
1
22
A comparison of generative #art by Dall-E 2 model (left) and Latent Diffusion LAION-400M (right) for the same input prompt. “A rabbit detective sitting on a park bench and reading a newspaper in a victorian setting” #dalle2 #laion400m #TextToImage
9
35
21
132
I legit thought that last week could never be with RQ-VAE, GLID-3, LAION-5B, StyleGAN XL, Make-a-Scene, CLIPMatrix and more in just one week! Oh well... PS: Next week I will try Dall-E 2 prompts compared to plenty of the most recent models. Stay tuned!
1
1
17