A short video/demo showing a quirky AI image generator that produces wild, low-fidelity but interesting images by chaining multiple generation steps. The speaker highlights examples (including a ‘crashed DALL·E’ style SpongeBob), notes that some pipelines use 8–10 steps, that multiple models are available, and that the tool is free to use.
This is probably the wildest AI image generator I found yet. Here's how it works. For example, this crashed DALI one is really interesting to me. So I don't know if I just say spongebob, king of sponges. And keep in mind these are crazy, quirky, weird. Okay, so this is not going to be high quality stuff. It's just going to be interesting and it's going to be wild. So as you can see, it always does multiple steps. And in some other examples here, it does like eight to 10 steps. So there you go. All hail SpongeBob. It's obviously generated a wilder prompt and you can regenerate this multiple times. There's various models here, and here you can see some results that other users just recently generated. I mean, look at that. This is not your typical Dall E generation, right? And you get that by combining a chain of multiple steps. So if you're into image generation and playing around, and if you're into weird results, then I guess you would enjoy doing this. This was completely for free, by the way.
