gptkbp:instanceOf
|
text-to-image AI model
|
gptkbp:announced
|
2022
|
gptkbp:assesses
|
human raters
|
gptkbp:author
|
gptkb:William_Chan
gptkb:Saurabh_Saxena
gptkb:Chitwan_Saharia
gptkb:David_Fleet
gptkb:Emily_Denton
gptkb:Jay_Whang
gptkb:Lala_Li
gptkb:Mohammad_Norouzi
gptkb:Sergio_Guadarrama
gptkb:Jonathan_Ho
gptkb:Tim_Salimans
|
gptkbp:citation
|
2022
high (as of 2024)
|
gptkbp:developedBy
|
gptkb:Google_Research
|
gptkbp:features
|
bias
harmful content
misuse potential
|
gptkbp:field
|
gptkb:artificial_intelligence
computer vision
natural language processing
|
gptkbp:focusesOn
|
photorealism
text-image alignment
|
gptkbp:hasDemo
|
limited access
|
https://www.w3.org/2000/01/rdf-schema#label
|
Imagen
|
gptkbp:improves
|
gptkb:Latent_Diffusion_Models
gptkb:VQ-GAN+CLIP
gptkb:DALL-E_2
|
gptkbp:input
|
text prompt
|
gptkbp:language
|
English
|
gptkbp:notablePublication
|
gptkb:Photorealistic_Text-to-Image_Diffusion_Models_with_Deep_Language_Understanding
|
gptkbp:notPubliclyAvailable
|
true
|
gptkbp:openSource
|
true
|
gptkbp:output
|
gptkb:illustrator
|
gptkbp:relatedTo
|
gptkb:DALL-E
gptkb:Midjourney
gptkb:Stable_Diffusion
|
gptkbp:uses
|
gptkb:T5-XXL_language_model
large language model
diffusion model
super-resolution diffusion models
|
gptkbp:website
|
https://imagen.research.google/
|
gptkbp:bfsParent
|
gptkb:DALL-E
gptkb:Stable_Diffusion
gptkb:Google_AI
|
gptkbp:bfsLayer
|
5
|