High-Fidelity Guided Image Synthesis with Latent Diffusion Models
— AK (@_akhaliq) December 1, 2022
abs: https://t.co/vhIhcCgB6q pic.twitter.com/Vkpk0fozr6
High-Fidelity Guided Image Synthesis with Latent Diffusion Models
— AK (@_akhaliq) December 1, 2022
abs: https://t.co/vhIhcCgB6q pic.twitter.com/Vkpk0fozr6
RGB no more: Minimally-decoded JPEG Vision Transformers
— AK (@_akhaliq) November 30, 2022
abs: https://t.co/w1WWGbPe5B pic.twitter.com/aEov50TPsD
Coder Reviewer Reranking for Code Generation
— AK (@_akhaliq) November 30, 2022
abs: https://t.co/0xaHE5jz4U pic.twitter.com/jKZHgKz409
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
— AK (@_akhaliq) November 29, 2022
abs: https://t.co/vEvAaM5KfE pic.twitter.com/SHH25hIVyc
AI twitter had erupted in controversy over Meta’s release of the Galactica demo. Is it a dangerous product, or was it unnecessarily maligned with overblown fears of harm? Here’s my take. https://t.co/XlCIo3S0mf
— Andrew Ng (@AndrewYNg) November 28, 2022
Magic Poser + Stable Diffusion 2.0’s Depth-to-Image
— hardmaru (@hardmaru) November 26, 2022
A blog post detailing the workflow of combining a pose maker software with Stable Diffusion 2.0’s Depth-to-Image model to have full control over the generated image.#StableDiffusion #StableDiffusion2https://t.co/VjtRZIfaBL pic.twitter.com/MGzG9cLJhW
Retrieval-Augmented Multimodal Language Modeling
— AK (@_akhaliq) November 24, 2022
abs: https://t.co/qSRxVEy546 pic.twitter.com/XLnBeDRoqN
Latent Video Diffusion Models for High-Fidelity Video Generation with Arbitrary Lengths
— AK (@_akhaliq) November 24, 2022
abs: https://t.co/TKMdZJTuef
project page: https://t.co/GBj7G7ddOT pic.twitter.com/BF08kAA2Yo
Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
— AK (@_akhaliq) November 24, 2022
abs: https://t.co/0woOqb8Y2J
project page: https://t.co/DgUiEEdmaY pic.twitter.com/BtIaAiMZOL
Inversion-Based Creativity Transfer with Diffusion Models
— AK (@_akhaliq) November 24, 2022
abs: https://t.co/xjed8TXDH5 pic.twitter.com/9fLJYMB3j8
Paint by Example: Exemplar-based Image Editing with Diffusion Models
— AK (@_akhaliq) November 24, 2022
abs: https://t.co/VYi4BQ2rxH pic.twitter.com/Kz3EZiI3PA
Kandinsky 2.0 - multilingual text2image latent diffusion model
— AK (@_akhaliq) November 23, 2022
Kandinsky 2.0 was trained on a large 1B multilingual set@huggingface model: https://t.co/dehtM8GABm
github: https://t.co/ALuydTezHj pic.twitter.com/26OC4twFKm