I was finally granted access to OpenAI’s AI image generator DALL-E 2!

Prompt: An oil-painting of an overexcited Asian woman testing DALL-E for the first time

Disclaimer: I am not an expert on any of the topics I shall discuss below, I am just curious and I like to experiment + learn. I’m using this platform to log my thoughts, ideas and whatever else comes to mind. Please take what I write with a pinch of salt, and always do your own research. I am not a very good writer either, so be prepared to be reading a lot of fluff. 

Anything I write that might be wrong, please do correct me but be polite about it, thank you! 

Date: Tuesday 28/06/22

On Monday 27th June I was finally granted access to OpenAI’s fabulous hyper performant AI Generator called DALL-E 2 after receiving an Insta DM from Natalie lol. Also I discovered in that process that DALL-E mini is irrelevant to DALL-E 2, the more you know! 

Before we could get started however, we had to join an onboarding call with the Community Manager who explained:

1. How the tool worked 
2. The rules and the constraints 
3. What OpenAI’s future plans are with DALL-E 2 
4.  Answer any questions we might have

Rules and constraints

The content policy we had to virtually ‘sign’, am I aloud to post this? idk, lmk

We had to virtually agree to a code of behaviour / contract behaviour / content policy which stated that under no circumstance were we to upload or generate images which could cause harm such as spam, self-harm, violence, harassment ect. and that we had to disclose the role of the AI at all times, not upload any images of public figures or recognisable / copyrighted characters or brands and of course, we were not aloud to sell any of the outcomes as digital files such as NFTs. 

I thought that was interesting since a lot of people complained about OpenAI’s ownership of all generated images and believed that they were ‘exploiting’ artists’ generated outcomes, but in reality I interpreted it as their way to ensure that nobody uses the tool in a dangerous way. By owning all the images, they can take down any creations which either harasses real-life folks such as celebrity deepfakes or any type of hate such as negative stereotypes or symbols.  

To ensure no wrongdoings, they have a bot who will ban you for generating censored content, and they can see all of your prompts and creations to doublecheck that you haven’t been banned for no reason. Fair dos. I also asked Natalie about menstruation, as a period activist I get frustrated at the sight of menstrual blood be more strongly censored than a blood from violence. Interestingly, she said they never tested the tool on period blood and that if I get banned from trying, she will obviously reinstate my account. So let’s write that one down for the list of experiments! 

Why artists? 

Interestingly however, OpenAI encouraged artists to push the potential of DALL-E 2 through unique, out-of-the-box prompts or through the process of integrating AI into their work. 

A lot of creatives are worried about losing their jobs to this tool, however I encourage folks to view DALL-E 2 as any other computer software, just like Photoshop, think about how the outcomes generated can act as either image references, food for thought, and be retaken, edited and modified to produce new forms of work, and how it can work within your already defined process as a designer or artist. If you’re into collage, then some generated outcomes can be played with and be apart of your process of breaking down the image, as an example. 

My first prompt EVER

Oh my god guysssss so these were my first prompts, I wanted to generate my own mood and excitement after SIX MONTHS of being on the waitlist and pestering OpenAI for weeks: 

First I tried: A screenshot of an overexcited British-Vietnamese-French designer esting DALL-E for the first time, but it gave me a dude :( 

Then I tried: An illustration of an overexcited British-Vietnamese-French woman testing DALL-E for the first time, but it gave me a blurry mess :(

Finally: An illustration of an overexcited Asian woman testing DALL-E for the first time, but I hated the style :(

So then I finessed my prompt to: An oil-painting of an overexcited Asian woman testing DALL-E for the first time

My second prompt EVER

Ok so it’s my brother’s birthday so I generated:

An oil-painting of an Asian DJ celebrating his 29th birthday at a Techno and Deep House club night:

The first image was his favourite!! and also:

An anime drawing of an Asian DJ celebrating his 29th birthday at a Techno and Deep House club night

He liked the first one most too :) 

Then I remembered that I was sharing a group chat with my sister too so I did one for her!!! She is a rheumatologist in South of France so: 

An oil-painting of an Asian female rheumatologist relaxing in Montpellier, France

Pretty good! 


A naturalist oil-painting of an Asian female rheumatologist relaxing in Montpellier, France

My brother said it looked like my mom lol 

1st Realisation: I must reach out to my friend and painter Caleb Sharpe to define a glossary of artistic terms because I just realised that I didn’t actually know what naturalism was in terms of painting.

My third experiment 

I decided to use their upload tool and upload an illustration to see what DALL-E 2 can generate using my image!

My new AI images instagram: Aie_aie_ai 

I created one just so I can log all of my creations, don’t want to clog up my main insta account. It’s called ‘Aie_aie_ai’ hehehe, if you get it, you get it. 

Also if you don’t, ‘aïe aïe aïe’ is like a French expression for when something is frustrating, annoying or problematic, and the single ‘aïe’ is for shit that hurts. 


  • I want to test menstruation-related images
  • I really want to test swear words in other languages 
  • I want to test generating buddha art or Vietnamese buddhist art