|
gptkbp:instanceOf
|
gptkb:model
|
|
gptkbp:application
|
creative content generation
custom avatar creation
personalized art
|
|
gptkbp:author
|
gptkb:Michael_Rubinstein
gptkb:Dilip_Krishnan
gptkb:Kfir_Aberman
gptkb:Nataniel_Ruiz
gptkb:Varun_Jampani
gptkb:Yuanzhen_Li
|
|
gptkbp:basedOn
|
text-to-image diffusion models
|
|
gptkbp:citation
|
high
|
|
gptkbp:developedBy
|
gptkb:Google_Research
|
|
gptkbp:enables
|
personalized image generation
|
|
gptkbp:field
|
gptkb:artificial_intelligence
computer vision
generative models
|
|
gptkbp:fineTuning
|
yes
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
DreamBooth
|
|
gptkbp:input
|
text prompt
reference images
|
|
gptkbp:language
|
English
|
|
gptkbp:notableFor
|
enabling few-shot personalization of generative models
personalizing pre-trained text-to-image models
generating images of a specific subject in different contexts
|
|
gptkbp:notablePublication
|
gptkb:DreamBooth:_Fine_Tuning_Text-to-Image_Diffusion_Models_for_Subject-Driven_Generation
|
|
gptkbp:openSource
|
no
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:relatedTo
|
gptkb:DALL-E
gptkb:Stable_Diffusion
gptkb:Imagen
text-to-image synthesis
|
|
gptkbp:releaseYear
|
2022
|
|
gptkbp:trainer
|
user-provided images
|
|
gptkbp:uses
|
gptkb:Stable_Diffusion
gptkb:Imagen
|
|
gptkbp:website
|
https://dreambooth.github.io/
|
|
gptkbp:bfsParent
|
gptkb:Diffusers
gptkb:PromptHero
gptkb:Stable_Diffusion_model
|
|
gptkbp:bfsLayer
|
6
|