Pedro Cuenca commited on
Commit
e1d1551
1 Parent(s): 36fdf01

Add demo screenshot

Browse files
Files changed (2) hide show
  1. README.md +2 -0
  2. img/demo_screenshot.png +0 -0
README.md CHANGED
@@ -9,6 +9,8 @@ language:
9
 
10
  This is an attempt to replicate OpenAI's [DALL·E](https://openai.com/blog/dall-e/), a model capable of generating arbitrary images from a text prompt that describes the desired result.
11
 
 
 
12
  This model's architecture is a simplification of the original, and leverages previous open source efforts and available pre-trained models. Results have lower quality than OpenAI's, but the model can be trained and used on less demanding hardware. Our training was performed on a single TPU v3-8 for a few days.
13
 
14
  ### Components of the Architecture
 
9
 
10
  This is an attempt to replicate OpenAI's [DALL·E](https://openai.com/blog/dall-e/), a model capable of generating arbitrary images from a text prompt that describes the desired result.
11
 
12
+ ![DALL·E mini demo screenshot](img/demo_screenshot.png)
13
+
14
  This model's architecture is a simplification of the original, and leverages previous open source efforts and available pre-trained models. Results have lower quality than OpenAI's, but the model can be trained and used on less demanding hardware. Our training was performed on a single TPU v3-8 for a few days.
15
 
16
  ### Components of the Architecture
img/demo_screenshot.png ADDED