Thanks for the suggestions. Agree that it’d be a much better user experience if the filter was more transparent.
4 Likes
AlexTully, in your specific case I believe it was the reference to Pachinko that the filters didn’t like: the prompt below gives no problems.
anime style drawing of an astonished young Australian man in a rural Japanese town, there is a Sukiya restaurant,there are Japanese yamamba ganguro girls with brightly coloured clothes, the girls coloured their skin dark, the girls have bleached blonde hair, the girls are wearing white lipstick, it’s a sunny day, there are cherry blossoms
1 Like
Thanks for the reply. The thing is that I’m too fearful of getting my account banned to play around with it and see what’s the problem is.
Some of the violation warnings are frankly bizarre.
a monkey on a skateboard
No problem
the taj mahal made of cheese
No problem
a monkey on a skateboard made of cheese
Violation threatening suspension.
6 Likes
I really don’t like these threatening messages especially since there is nothing wrong with some of the queries, such as: cat licking dead android’s body in a cyberpunk closet, digital art
4 Likes
I requested “Circles and squares being created in an assembly line” and was flagged. Then I used the placeholder prompt of “an impressionist oil painting of sunflowers in a purple vase” and was flagged. Then I hit the surprise me button and the prompt “a sea otter with a pearl earring” by Johannes Vermeer". It seems that Dall-E 2 is flagging everything, including the suggested prompts lol.
Well, looks like I am unable to use it…
3 Likes
Same for me - flagging everything, including “Surprise me” prompts. I just stopped and hoping that the issue will be resolved soon.
3 Likes
Today it’s working again. Have no idea what happened. Flagged prompts have been deleted from my history so I can not review them to figure out what could have gone wrong there. Anyway, I’m happy everything seems to be working fine again.
1 Like
How long does it usually take to get a account reactivated after sending out the appeal?
I’m itching to play around with DALLE again 
I have already been warned several times; twice for things I would expect it to hit like politics, and history that is being revised to airbrush out all violence. So no artificial intelligence is permitted to paint the death of Stalin, for instance, even if peaceful. I translated a Han Dynasty book and I’m using AI to produce illustrations. Unfortunately I have already hit censorship because drums were daubed with blood and sacrifices were made, etc etc. So it will not be possible to illustrate religious works like the Jiao Shi Yi Lin or the Bible. Too much violence. Kinda makes I’m glad I lived to see this kind of program but also glad I’m old and won’t be around for the logical conclusion of this censorship and prevailing ignorance of history
1 Like
I got an content violation warning for this…
"Girl riding on the back of a giant shitzhu dog. "
1 Like
Also got one. “Thousands of mink running on a field”
I wonder if it’s due to the news during covid and mink that somehow trigger the AI.
1 Like
i got one for “Nvidia simulation of a very hairy cube next to a glass ball with caustics, studio lighting”… wtf?
1 Like
it has the bad S word in it, thats obv the problem. doubt it would give the error for a pomeranian or pug etc
Exactly. It really is just a stupid wordlist for now and flags everything.
I have thought of two possible ways that OpenAI could solve this problem:
- Silent flagging and then an actual account review by staff after X flaggings
- Finetune a Davinci model on thousands of prompts on ACCEPTABLE and RISKY. It will have much higher reliability.
Honestly I don’t know why OpenAI still haven’t thought of a simple and effective solution like point number 2 and insisted on a dumb (aka non-intelligent) wordlist. The cost of running this model on a single user-requestet prompt is negligible, even more after it’s been fine-tuned.
also given enough fine tuning and effort, you could probably make it work with babbage or curie, further reducing the cost. I’m sure they have their reasons for using a wordlist but having somthing that can understand context would help a ton. Maybe use a wordlist as a backup gpt fails? The added latency shouldnt be a problem since it already takes a bit of time to generate the image.
1 Like
I highly doubt that. It’s simply easier to implement (no train - just yeet wordlist in and done) and costs nothing, but that’s not a valid reason imo.
Meanwhile tens of people have already been banned for no reason at all, hurting OpenAI’s revenue. Most don’t come back after that, considering that there are alternatives which are cheaper, work almost as good and the user doesn’t need to wait a team’s manual decision to get unbanned.
It’s kinda sad. I love OpenAI, but this decision in particular I just don’t get it.
2 Likes
I had my account suspended, filed an appeal a week ago. Was just trying to edit the rib of an angel with inpainting. I can’t figure out anything wrong I’ve done.
2 Likes
I got revoked for a description of chicken in sauce which I had Chatgpt write… which part of this triggered the filter? Chatgpt violated policies of Dall-e.
“A sleek, modern restaurant plate is set with a beautifully plated portion of chicken in creamy white sauce. The chicken is tender and juicy, with a golden, crispy skin. The sauce is a pale, creamy white color, with swirls of dark, earthy spices throughout. A bed of creamy mashed potatoes is spooned onto the plate, and a sprig of fresh herbs adds a pop of vibrant green color. The dish is garnished with a sprinkle of crispy fried onions, adding a crunchy texture to the dish. The plate is illuminated by a dim, atmospheric light, and a glass of chilled white wine sits nearby, ready to be sipped alongside the dish.”
would be my guess… in context it’s fine, but out of context… well, I’ll leave that to your imagination. Haha.
You might try a shorter prompt, too.
Good luck!
1 Like