Will DALLE-3 be able to generate an image of a crowd without people blending into each other?
19
199
Ṁ1.1kṀ410
resolved Jan 1
Resolved
YES1D
1W
1M
ALL
"Draw me the image of 30 people standing in a line"
"Draw me an image of 10 people holding hands in a circle"
I will keep the #people to less than 50 for my prompts and the composition relatively simple.
Resolves YES if DALLE-3 success rate is 40% or more. I will test it roughly 10 times. If >80% of the people in the image are generated correctly without weird morphing effects, then I count that as a "YES" for that particular image.
10 times means 10 prompts. If 4 images are generated to a prompt, then we're testing on 40 images.
Get Ṁ600 play money
Related questions
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ144 | |
2 | Ṁ82 | |
3 | Ṁ37 | |
4 | Ṁ18 | |
5 | Ṁ8 |
Sort by:
@DanMan314 it's about the morphing thing, the number of people doesn't matter as long as it's in the correct ballpark
Related questions
Will DALL-E 3+ consistently generate accurate images from the prompt "yellow ocean, blue sand" before 2025?
40% chance
Will DALL-E 4 be able to generate an image with 10 English words without making any mistakes, at least 50% of the time?
54% chance
Dalle-3 via GPT-4 defaults to making more than one image at a time, by mid 2024
67% chance
Will OpenAI release a tool to identify images generated by DALL.E? (in 2024)
52% chance
A public AI generator can correctly make images of complex 3d object stacking, Jun 1 2024
20% chance
Will OpenAI release an image model better than DALL-E 3 in 2024?
84% chance
Will any image model available to the public be able to reliably produce images of every regular polygon before 2026?
9% chance
Will there be an open source, uncensored AI image generator with the same or greater quality as DALLE-3 by end of 2025?
88% chance
By 2030, will Ai picture generators be able to do basic geometry and projections?
89% chance
Dalle-3 via openai's website can directly annotate images by mid 2024
4% chance