We don't want to build a "replace artists" sort of tool. We want to build software that makes the lives of everyone easier. If you can afford an artist, then we want to give that artist superpowers. If you can't, then we'd like to give you a tool that still allows you to create!
CREATIVE AI
-
AI Thumbnail Generation: Protecting Creator Jobs While Saving Time
By
–
2. We wanted to save creators and marketing executives time and money if they didn't have a thumbnail artist. But I was also keen on protecting these jobs: If we could make ALSO make thumbnail artist lives better and give them a base they can build on top of, that would be a win!
-
Reimagining AI-Powered Thumbnail Generation from Ground Up
By
–
I was helping an excellent team on building out a different AI tool for thumbnails. Two things went on in my head: 1 .The approach was great, but I wasn't happy with the results. I wanted a ground up reimagining of thumbnail creation, including a brand new model to do so.
-
AlphaCTR Launches AI-Powered Thumbnail and Ad Creative Generator
By
–
New product announcement: We're excited to launch AlphaCTR, a new way to create thumbnails and ad creatives with minimal effort.
-
Paul McCartney Completes New Beatles Song Using Artificial Intelligence
By
–
The Contravesial Voice of Artificial Intellgence Paul McCartney Says New Beatles Song Finished With Help From Artificial Intelligence https://
buff.ly/43NRg4q
#TheBeatles #ai #ArtificialIntelligence #Machinelearning #deeplearning #art -
ATT3D: Advanced Text-to-3D Object Synthesis Technology
By
–
ATT3D: Amortized Text-to-3D Object Synthesis
— AK (@_akhaliq) 14 juin 2023
paper page: https://t.co/jINaEFQvWR
Text-to-3D modelling has seen exciting progress by combining generative text-to-image models with image-to-3D methods like Neural Radiance Fields. DreamFusion recently achieved high-quality results… pic.twitter.com/uFMHgImJCEATT3D: Amortized Text-to-3D Object Synthesis paper page: https://
huggingface.co/papers/2306.07
349
… Text-to-3D modelling has seen exciting progress by combining generative text-to-image models with image-to-3D methods like Neural Radiance Fields. DreamFusion recently achieved high-quality results -
Neural Scene Chronology: Time-Varying 3D Reconstruction from Internet Photos
By
–
Neural Scene Chronology
— AK (@_akhaliq) 14 juin 2023
paper page: https://t.co/oUdnOhTYls
In this work, we aim to reconstruct a time-varying 3D model, capable of rendering photo-realistic renderings with independent control of viewpoint, illumination, and time, from Internet photos of large-scale landmarks.… pic.twitter.com/pmIuSzH6LNNeural Scene Chronology paper page: https://
huggingface.co/papers/2306.07
970
… In this work, we aim to reconstruct a time-varying 3D model, capable of rendering photo-realistic renderings with independent control of viewpoint, illumination, and time, from Internet photos of large-scale landmarks. -
AI Creates Perfect Meal from Every Western European Country
By
–
AI asked to make the perfect Meal from every Western European Country 1. Italian
-
Instant Multi-View Head Capture through Learnable Registration
By
–
Instant Multi-View Head Capture through Learnable Registration
— AK (@_akhaliq) 14 juin 2023
paper page: https://t.co/cgIfWuUvki
Existing methods for capturing datasets of 3D heads in dense semantic correspondence are slow, and commonly address the problem in two separate steps; multi-view stereo (MVS)… pic.twitter.com/8h3YoWOHIwInstant Multi-View Head Capture through Learnable Registration paper page: https://
huggingface.co/papers/2306.07
437
… Existing methods for capturing datasets of 3D heads in dense semantic correspondence are slow, and commonly address the problem in two separate steps; multi-view stereo (MVS) -
Rerender A Video: Zero-Shot Text-Guided Video Translation
By
–
Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
— AK (@_akhaliq) 14 juin 2023
paper page: https://t.co/Ac6ct1naXx
Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring… pic.twitter.com/Il8xSgsW1kRerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page: https://
huggingface.co/papers/2306.07
954
… Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring