
Reliable compositions (AI using prepositions) via text-to-image by the end of 2024
4
130Ṁ92Jan 1
29%
chance
1H
6H
1D
1W
1M
ALL
Tex-to-image AIs learn to generate correct compositional images.
Burden of proof on those betting YES.
Resolves to YES if all conditions are met:
Free to use model
Correct images (at least one out of 3 first drawn) for at least 8 out of 10 prompts
Prompts consisting of pairs of English nouns (only those representing objects/living organisms, etc; not concepts, ideas) connected with prepositions ("a"/"the" optional)
Nouns randomly selected from list of 5000 most common English words filtered to nouns (if selects noun not conforming to #3 , select another pair)
Prepositions randomly selected from the list: [on,under,in,behind]
Example: "a table on a vase", "a table in a vase"
Clarifications and discussions in the comments.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
People are also trading
Related questions
Which company has best Text-to-Image AI model end of 2025? (Artificial Analysis Leaderboard)
Will there be realistic AI generated video from natural language descriptions by the start of 2026?
56% chance
Will AI make it possible to autoname all images in a folder based on the image contents by EOY 2025
95% chance
Will AI be able to create art in a "human-like way" within Photoshop, GIMP, or Paint.NET by the end of 2025?
40% chance
Will AI be able to describe the state of a chessboard from an image before 2026?
85% chance
Before 2030, will an AI system be able to solve compositional problems of arbitrary depth?
47% chance
AI generates better alt text for 90% of test images by June 30, 2026?
65% chance
Will an AI agent be able to draw a mid-2024-diffusion-model-quality image in a standard drawing program by 2027?
60% chance
Will AI achieve superintelligence in music composition by 2026?
17% chance
AI solves the Abstraction and Reasoning Corpus (ARC) by 2028
34% chance