Luis Rivera πŸƒ (@luisriverag) header
Luis Rivera πŸƒ (@luisriverag) profile picture
Europe
Joined July 2008
Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)Photo by Luis Rivera πŸƒ (@luisriverag)
A few weeks ago I started a prompt based blog: 1. I prompt once 2. I publish whatever the text bot replies & include the prompt at the bottom 3. I feed the first paragraph to an image bot to illustrate the post If you don't like posts, blame the bots ghost.luisriverag.com
1
512
So long and thanks for all the fish! #MyTwitterAnniversary
1
530
😳
AI Johnny Cash sings "Barbie Girl"
234
Luis Rivera πŸƒ retweeted
New mortgage math is brutal. Say you buy a $1m house with $200k down at a 7% rate ($800k mortgage). Over the first three years you pay $193k ($5,322/mo.) After those $193k of payments your $800k mortgage is now at $774.5k. You paid $166k in interest, $25.5k in principle.
1,847
3,353
748
27,472
7,738,957
Luis Rivera πŸƒ retweeted
Unbelievable A Russian submarine commander was assassinated on his run yesterday He was posting his workouts on Strava! One of the people who liked the posts, was the Chief of Intelligence of Ukraine
531
2,842
1,086
26,865
6,489,733
Luis Rivera πŸƒ retweeted
Individual investors doing more to support compute-intensive startups than most governments. (Very cool project!)
Daniel and I have setup a cluster for startups: andromedacluster.com
1
13
63
12,959
Luis Rivera πŸƒ retweeted
xkcd predicted AI panic in 2013
1
12
1
67
7,779
Luis Rivera πŸƒ retweeted
πŸ€”πŸ€”πŸ€”
1
1
5
1,304
Luis Rivera πŸƒ retweeted
Putin reportedly has fled Moscow. You know who didn't flee the capital ahead of advancing Russian forces? President Zelenskyy.
5,838
5,662
506
40,947
2,424,230
Gensler seeing the price go up.
15
14
201
17,780
"Europe has fallen behind America and the gap is growing" ft.com/content/80ace07f-3acb…
117
Luis Rivera πŸƒ retweeted
Just had a conversation with claude-100k that cost me $4. Sounds like a lot, until you realize the equivalent done by a human would have cost me easily $200 (which I’d have gladly paid).
14
19
4
261
116,837
Luis Rivera πŸƒ retweeted
Things are going really well at your company when the CEO writes "from where i sit it just looks like magical money appears".
1
30
2
190
33,030
Thanks for all the fish!
After 11 fateful voyages at sea, Pirate Summit co-founder Manuel Koelman decides its time to scuttle this ship. Here’s why. buff.ly/3J7VH1W
170
Luis Rivera πŸƒ retweeted
seven more major tokens have been named securities by the SEC in the lawsuit against coinbase: CHZ (#64), FLOW (#60), ICP (#31), NEAR (#37), VGX (#444), DASH (#85), and NEXO (#92)
2
7
36
7,532
Luis Rivera πŸƒ retweeted
HeadSculpt: Crafting 3D Head Avatars with Text paper page: huggingface.co/papers/2306.0… Recently, text-guided 3D generative methods have made remarkable advancements in producing high-quality textures and geometry, capitalizing on the proliferation of large vision-language and image diffusion models. However, existing methods still struggle to create high-fidelity 3D head avatars in two aspects: (1) They rely mostly on a pre-trained text-to-image diffusion model whilst missing the necessary 3D awareness and head priors. This makes them prone to inconsistency and geometric distortions in the generated avatars. (2) They fall short in fine-grained editing. This is primarily due to the inherited limitations from the pre-trained 2D image diffusion models, which become more pronounced when it comes to 3D head avatars. In this work, we address these challenges by introducing a versatile coarse-to-fine pipeline dubbed HeadSculpt for crafting (i.e., generating and editing) 3D head avatars from textual prompts. Specifically, we first equip the diffusion model with 3D awareness by leveraging landmark-based control and a learned textual embedding representing the back view appearance of heads, enabling 3D-consistent head avatar generations. We further propose a novel identity-aware editing score distillation strategy to optimize a textured mesh with a high-resolution differentiable rendering technique. This enables identity preservation while following the editing instruction. We showcase HeadSculpt's superior fidelity and editing capabilities through comprehensive experiments and comparisons with existing methods.
42
1
180
62,118