Will Stable Diffusion 3 be able to get DeWeese lab's "red conical block on top of..." prompt a majority of the time?
resolved Apr 17

Gary Marcus made a post discussing the Imagen and DALLE-2 model's inability to fully grasp language, particularly around relational undestanding of objects in a prompt: https://garymarcus.substack.com/p/horse-rides-astronaut

Stability AI just released Stable Diffusion 3 (https://stability.ai/news/stable-diffusion-3), which they claim has "greatly improved performance in multi-subject prompts, image quality, and spelling abilities".

Once publicly available, I will run this prompt from DeWeese lab that is discussed heavily in the post:

A red conical block on top of a grey cubic block on top of a blue cylindrical block, with a green cubic block nearby

I will produce 10 images. If 5 or more of the images match the prompt exactly, following the color, shape, and positions specified in the prompt, this market resolves YES. Otherwise, it resolves NO.

I will not bet in this market in case there is ambiguity on some of the images.

Get Ṁ200 play money

🏅 Top traders

#NameTotal profit
Sort by:

Image 1 (fail - noncubic green block, blue block not cylinder/not on bottom).

Image 2 (fail - noncubic green block, blue block not cylinder)

Image 3 (fail - noncubic green block)

Image 4 (fail - so close! grey block not on top of blue cylinder)

Image 5 (obviously fail)

Image 6 (obviously fail)

@DanMan314 I'm stopping after 6/6 failures to save the credits.


Some evidence that SD3 is pushing even farther forward than DALLE-3 in accurately following prompts!