![]() Now do one final pass considering the input image again, making sure to include everything from it in the output one, too. Then add even more detail by reviewing what we reviewed before. Then "compress" this data using abbreviations, shortenings, artistic metaphors, references to things which might help others understand it, labels and select pull-quotes. Now think about the emotions - what is everyone feeling and thinking and doing towards each other? Now, take all that data and think about a very long, detailed summary including all elements. Now write out the composition and organization of the image in terms of placement, size, relationships, focus. Now think about the theme of the image and write that down, too. List them in your mind including position, style, shape, texture, color, everything else essential to convey their meaning. Look at this image and extract all the vital elements. This kind of makes sense as a way to prevent new sign-ups from blowing thousands of dollars of cap mistakenly. Sometimes you also really do hit ratelimits.Īlso, you can't raise your rate limits until you prove it by having paid over X amount to openai. If you send too long, or too risky a prompt, or the image it generates is randomly too risky, you either get told about it or lied to that you've hit rate limits. Overall the extreme content filtering and lying error messages are not ideal will probably improve in the future. Hyper-long + max detail + compression + telling it to cut all that down to 12 words - This seems okay. Hyper-long + max detail + compression - This shows that with enough text, it can do a really good job of reproducing very, very similar images The "create text version of image" prompt matters a ton. Prompt: "A sugar skull who once played a gig at CBGB in New York City, a sentient mushroom, and two garden gnomes converse about the boundaries of artificial intelligence." Prompt: "A sentient mushroom, a sugar skull who once played a gig at CBGB in New York City, and two garden gnomes converse about the boundaries of artificial intelligence." Prompt: "Two garden gnomes, a sentient mushroom, and a sugar skull who once played a gig at CBGB in New York City converse about the boundaries of artificial intelligence." ![]() Thank you for putting this together and sharing it! In any case, playing around with this tool has been enjoyable and a fun use of API credits. But that's wild speculation based on an extremely small sample of results. I'll also speculate that "gnomes" (and their derivations) and "cosmic images" are over-represented as subjects in the underlying training data. Make it weirder."įrom what you'll see in the results there's possible evidence of bias towards the first subject listed in a prompt, making it the object of fixation through the subsequent iterations. Just return the prompt, don't say anything else. GPT4V instructions for all tests: "Write a prompt for an AI to make this image. I was curious if two subject prompts behaved different from three subject, so I've run three additional tests, each with the same three subjects and general prompt structure + instructions, but swapping the position of each subject in the prompt. The goat one (which again, was an idea from one of my kids) was by far the best in terms of "progression to insanity" that I got out of the model. ![]() Earlier attempts without that instruction were still cool, but what I noticed was that once you ask it to intensify every adjective, you pretty much go to 11 within the first iteration or two - so you wind up having 1 image of a silly cat or goat and then 7 more images of world-shattering kaiju. I played with it a bit before I got results I liked - one of the key factors, I think, was giving the model permission to add stuff to the image, which introduced enough variation between images to have a nice sense of progression. Really oversell the intensity factor, and feel free to add extra elements to the existing image to amp it up. Just return the prompt, don't say anything else, but also, increase the intensity of any adjectives, resulting in progressively more fantastical and wild prompts. > Write a prompt for an AI to make this image. Thanks! This was the custom prompt I used: ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |