CHAIR INTELLIGENCE

HUMAN FORM V AI RECOGNITION

BY: ME + AI

Dall-e and Runway AI models interpret images of human bodies as a body but differently: a body suggesting a function and as a body in terms of parts. Dall-e was able to fill in the image, recognizing where a “chair” would be placed based on the composition of the image and our body in space. Whereas runway led to uncanny images dissecting components like using human arms for the arms of a chair. A possibility that was unexpected but also logical in relating the function of arms between both the human body and a chair, rather than the function of sitting we assumed Runway would recognize.

DATASET

How many ways can you “sit” on a chair? Everything, except the “sitting” body, is extracted from the image. The bodies become a dataset in Runway that can be used to generate new images with text or image prompts. 

3.png
2.png
4.png
1.png
5.png
6.png
7.png
9.png
10.png
11.png
14.png
8.png
15.png
16.png
18.png
19.png
12.png
25.png
13.png
17.png
20.png
21.png
22.png
23.png
24.png
26.png
27.png
28.png
29.png
30.png

+

PROMPT : “To Sit is defined as to be in a position in which one's weight is supported by one's buttocks rather than one's feet and one’s back is upright”

DALLE

RUNWAY