|
gptkbp:instanceOf
|
gptkb:model
|
|
gptkbp:basedOn
|
GPT architecture
transformer neural network
|
|
gptkbp:category
|
gptkb:artificial_intelligence
gptkb:machine_learning
computer vision
deep learning
natural language processing
generative AI
text-to-image model
image synthesis
|
|
gptkbp:citation
|
https://arxiv.org/abs/2102.12092
|
|
gptkbp:developedBy
|
gptkb:OpenAI
|
|
gptkbp:features
|
content filters
output moderation
prompt moderation
|
|
gptkbp:firstReleased
|
2021
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
OpenAI DALL-E
|
|
gptkbp:input
|
text prompt
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
proprietary
|
|
gptkbp:limitation
|
may generate biased or inappropriate images
may misinterpret ambiguous prompts
cannot generate photorealistic faces of real people
|
|
gptkbp:mediaCoverage
|
gptkb:BBC
gptkb:The_Verge
gptkb:Wired
gptkb:New_York_Times
|
|
gptkbp:memiliki_tugas
|
text-to-image generation
|
|
gptkbp:mobileAppAvailable
|
yes
|
|
gptkbp:notableExample
|
a baby daikon radish in a tutu walking a dog
a two-story pink house shaped like a shoe
an armchair in the shape of an avocado
|
|
gptkbp:notableFor
|
generating novel images from textual descriptions
|
|
gptkbp:notableUser
|
gptkb:artist
gptkb:fashion_designer
gptkb:researchers
educators
marketers
|
|
gptkbp:openSource
|
no
|
|
gptkbp:output
|
gptkb:illustrator
|
|
gptkbp:platform
|
gptkb:Microsoft_Bing_Image_Creator
gptkb:Microsoft_Designer
gptkb:ChatGPT_Plus
gptkb:OpenAI_API
|
|
gptkbp:relatedTo
|
gptkb:OpenAI_CLIP
gptkb:OpenAI_GPT-3
|
|
gptkbp:successor
|
gptkb:DALL-E_2
gptkb:DALL-E_3
|
|
gptkbp:trainer
|
text-image pairs
|
|
gptkbp:usedFor
|
gptkb:art
gptkb:design
gptkb:illustrator
gptkb:data_visualization
creative image generation
|
|
gptkbp:website
|
https://openai.com/research/dall-e
|
|
gptkbp:bfsParent
|
gptkb:Midjourney
|
|
gptkbp:bfsLayer
|
5
|