11–20 of 153 posts
Can I use NLP to generate input for DALL-E 2? That would be cool.
I want to see a few iterations of describing an image with AI, generating it, describing it again, generating it... Like when passing a piece of text through Google translate back and forth.
Can I use NLP to generate input for DALL-E 2? That would be cool.
I want to see a few iterations of describing an image with AI, generating it, describing it again, generating it... Like when passing a piece of text through Google translate back and forth.
I had the same trouble. In my experiment I wanted to generate a Porco Rosso style seaplane. illustration. Sadly none of the generated pictured had the whole of the airplane in them. The wingtips or the tail always got left off.
I found this method to be a reliable workaround: I have downloaded the image I liked the most. Used an image editing software to extend the image in the direction I wanted it to be extended and filled the new area with a solid colour. Cropped a 1024x1024 size rectangle such that it had about 40% generated image, and 60% solid colour. Uploaded the new image and asked DALL-E to infill the solid area while leaving the previously generated area unchanged. Selected from the generated extensions the one I liked the best, downloaded it and merged it with the rest of the picture. Repeated the process as required.
You need a generous amount of overlap so the network can figure out which parts is already there and how best to fit the rest. It's a good idea to look at the image segment you need to be infilled. If you as a human can't figure out what it is you are seeing, then the machine won't be able to figure it out either. It will generate something, but it will look out of context once merged.
The other trick I found: I wanted to make my picture a canvas print, and thus I needed a higher resolution image. Higher even then what I can reasonably hope with the above extension trick. What I did is that I have upscaled the image (used bigjpg.com, but there might be better solutions out there.) After that I had a big image, but of course there weren't many small scale details now on it. So I have sliced it up to 1024x1024 rectangles, uploaded the rectangles to DALL-E and asked it to keep the borders intact but redraw the interior of them. This second trick worked particularly well on an area of the picture which shown a city under the airplane. It has added nice small details like windows and doors and roofs with texture without disturbing the overall composition.
What I did:
I wonder what Gary Marcus or Filip Pieknewski think about it. Surely they must be eating crow.
I mostly use it and Midjourney for material for my DnD campaign, but I'm going to need to do a little more work to make the whole thing coherent. Only tried it once and it was okay.
The interesting part is that it can do things like "female ice giant" reasonably whereas google will just give you sexy bikini ice giant for stuff like that which is not the vibe of my campaign!
Is there randomization or will the same prompts produce the same image sets?
Can I use NLP to generate input for DALL-E 2? That would be cool.
Even when I re-used the exact prompts from the DALL-E Prompt Book, I didn't get anything near the level of quality and fidelity to the prompt that their examples did.
I know it's not a scam, because it's clearly doing amazing stuff under the hood, but I went away thinking that it wasn't as miraculous as it was claimed to be.