Midjourney will be able to create images of people with different facial expressions before 2024
11
107
Ṁ1.4KṀ150
resolved Jan 3
Resolved
NO1D
1W
1M
ALL
On Jan 1st 2024 I will run this prompt in midjourney five times with random seeds: "a portrait of a smiling man and his frowning, sad wife"
I will run it with all the default options, aspect ratio 3:2, and the most advanced general model a paid subscriber can get under 100$ a month. If at least 50% of the resulting images successfully make the man look happy and the wife look unhappy, the claim resolves True.
The current best midjourney model is v5.1, and today the success rate is 0%. Five images generated with these settings are inlined below. Currently, midjourney doesn't track individual subjects clearly in this way.
Initial set of images from 5/10/2023 here:
Get Ṁ200 play money
Related questions
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ264 | |
2 | Ṁ19 | |
3 | Ṁ3 |
Sort by:
Related questions
Instant deepfakes of anyone (doing anything) by the end of 2027?
73% chance
Instant deepfakes of anyone before the end of 2024?
18% chance
Midjourney can draw a simple stack of colored shapes by mid 2024
70% chance
Midjourney v7 comes out by mid 2024
37% chance
A public AI generator can correctly make images of complex 3d object stacking, Jun 1 2024
23% chance
Midjourney can create correct text in images by June 1 2024
95% chance
Some public image generation system can create an ordered circle of random numbers by end 2024
24% chance
Midjourney integration with Twitter by eoy 2024
29% chance
Midjourney images can be effectively watermarked by 5/2025
22% chance