Skip to main content

alignDRAW - the first text-to-image artwork from 2015.

By early 2015, neural networks had mastered the art of 'image-to-text' and could create natural language captions for images. Flipping this process, and turning text into image, was a much more complex challenge solved by 19-year old prodigy Elman Mansimov's alignDRAW model.

Fellowship is pleased to present a special release of both print editions and fully on-chain NFTs of this historical artwork, containing all the original images created in 2015.

"alignDRAW images can be compared to the first fixed photographs taken by Niepce in 1826-1827." Dr Lev Manovich

"These images represent the birth of text prompt AI generated imagery." Darius Himes, Christie's

What 2015 provenance is there?

The 'Paper Prompts' can be found in the published academic paper, 'Generating Images from Captions with Attention', submitted in November 2015. You can view the paper here:

https://arxiv.org/abs/1511.02793

The lead author of the paper was Elman Mansimov and the co-authors were Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov.

The 'Process Prompts' can be found on the University of Toronto website. Using archive.org you can see also see these images displayed in November 2015:

https://bit.ly/aligndraw-toronto-edu

alignDRAW collection image

alignDRAW (2015). The first text-to-image artwork.

By early 2015, neural networks had mastered the art of 'image-to-text' and could create natural language captions for images. Flipping this process, and turning text into image, was a much more complex challenge solved by 19-year old prodigy Elman Mansimov's alignDRAW model.

DAILY, in partnership with Fellowship, is pleased to present a special release of fully on-chain* NFTs of this historical artwork, containing all the original 32x32 pixel images.

“These images represent the birth of text prompt AI generated imagery.” - Darius Himes, Christie’s

“alignDRAW images can be compared to the first fixed photographs taken by Niépce in 1826-1827.” - Dr Lev Manovich

*We created an architecture that allowed for the progressive on-chain storage of data and images, through a phased roll-out during periods of lower gas prices.

UPDATE: as of Mon 20th May 2024 alignDRAW is fully on-chain.

Category Art
Contract Address0x9cf0...c747
Token ID
Token StandardERC-721
ChainEthereum
Last Updated3 days ago
Creator Earnings
5%

A toilet seat sits open in an empty bathroom #64

visibility
12 views
  • Price
    USD Price
    Quantity
    Expiration
    From
  • Price
    USD Price
    Quantity
    Floor Difference
    Expiration
    From
keyboard_arrow_down
Event
Price
From
To
Date

A toilet seat sits open in an empty bathroom #64

visibility
12 views
  • Price
    USD Price
    Quantity
    Expiration
    From
  • Price
    USD Price
    Quantity
    Floor Difference
    Expiration
    From

alignDRAW - the first text-to-image artwork from 2015.

By early 2015, neural networks had mastered the art of 'image-to-text' and could create natural language captions for images. Flipping this process, and turning text into image, was a much more complex challenge solved by 19-year old prodigy Elman Mansimov's alignDRAW model.

Fellowship is pleased to present a special release of both print editions and fully on-chain NFTs of this historical artwork, containing all the original images created in 2015.

"alignDRAW images can be compared to the first fixed photographs taken by Niepce in 1826-1827." Dr Lev Manovich

"These images represent the birth of text prompt AI generated imagery." Darius Himes, Christie's

What 2015 provenance is there?

The 'Paper Prompts' can be found in the published academic paper, 'Generating Images from Captions with Attention', submitted in November 2015. You can view the paper here:

https://arxiv.org/abs/1511.02793

The lead author of the paper was Elman Mansimov and the co-authors were Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov.

The 'Process Prompts' can be found on the University of Toronto website. Using archive.org you can see also see these images displayed in November 2015:

https://bit.ly/aligndraw-toronto-edu

alignDRAW collection image

alignDRAW (2015). The first text-to-image artwork.

By early 2015, neural networks had mastered the art of 'image-to-text' and could create natural language captions for images. Flipping this process, and turning text into image, was a much more complex challenge solved by 19-year old prodigy Elman Mansimov's alignDRAW model.

DAILY, in partnership with Fellowship, is pleased to present a special release of fully on-chain* NFTs of this historical artwork, containing all the original 32x32 pixel images.

“These images represent the birth of text prompt AI generated imagery.” - Darius Himes, Christie’s

“alignDRAW images can be compared to the first fixed photographs taken by Niépce in 1826-1827.” - Dr Lev Manovich

*We created an architecture that allowed for the progressive on-chain storage of data and images, through a phased roll-out during periods of lower gas prices.

UPDATE: as of Mon 20th May 2024 alignDRAW is fully on-chain.

Category Art
Contract Address0x9cf0...c747
Token ID
Token StandardERC-721
ChainEthereum
Last Updated3 days ago
Creator Earnings
5%
keyboard_arrow_down
Event
Price
From
To
Date