Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
— AK (@_akhaliq) November 23, 2022
abs: https://t.co/CgS0RDlI4U pic.twitter.com/A7Tplszo86
Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
— AK (@_akhaliq) November 23, 2022
abs: https://t.co/CgS0RDlI4U pic.twitter.com/A7Tplszo86
DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models
— AK (@_akhaliq) November 23, 2022
abs: https://t.co/erijwxpeRW
project page: https://t.co/dLjkJDBfJa pic.twitter.com/1eCXpTsGKT
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
— AK (@_akhaliq) November 22, 2022
abs: https://t.co/xJpOrT5TtR
github: https://t.co/p9hNRPU556@huggingface model: https://t.co/4qTRGDW7ws pic.twitter.com/AzVocAs40B
ClipCrop: Conditioned Cropping Driven by Vision-Language Model
— AK (@_akhaliq) November 22, 2022
abs: https://t.co/CzRBL0hgaz pic.twitter.com/IdfYMYGOeX
SinFusion: Training Diffusion Models on a Single Image or Video
— AK (@_akhaliq) November 22, 2022
abs: https://t.co/3ssJ6zns6y
project page: https://t.co/J84X97idzV pic.twitter.com/MscHbSHoSL
Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
— AK (@_akhaliq) November 22, 2022
abs: https://t.co/Id4oqu0omU pic.twitter.com/hpmr6EtL8z
Explainability Via Causal Self-Talk
— AK (@_akhaliq) November 21, 2022
abs: https://t.co/731kBBetU7 pic.twitter.com/8Jc0ShRz6k
A Structure-Guided Diffusion Model for Large-Hole Diverse Image Completion
— AK (@_akhaliq) November 21, 2022
abs: https://t.co/WSgCK892Rn pic.twitter.com/bDl3Z4nxOb
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model Gallery@huggingface demo: https://t.co/xmAyV8U0Lq pic.twitter.com/GO3sSqBnLc
— AK (@_akhaliq) November 19, 2022
DiffusionDet: Diffusion Model for Object Detection
— AK (@_akhaliq) November 18, 2022
abs: https://t.co/GBu4bZPwKp
github: https://t.co/bWHxGxayjB pic.twitter.com/7a8lfNaqp9
I Can't Believe There's No Images! Learning Visual Tasks Using only Language Data
— AK (@_akhaliq) November 18, 2022
abs: https://t.co/fxIgCaiDES pic.twitter.com/YzhEQ2CoTr
InstructPix2Pix: Learning to Follow Image Editing Instructions
— AK (@_akhaliq) November 18, 2022
abs: https://t.co/UqsKEMRkkx
project page: https://t.co/WTFqVkkJli
InstructPix2Pix, trained on generated data, and generalizes to real images and user-written instructions at inference time pic.twitter.com/YPHY7zmBqb