BoM/TWS Message Forum

So, in essence, you used it as a tool. That's cool.

I've been experimenting on using a different app, specifically because of its face-swapping options. I started with some face-swaps, and while a few results ended up cursed, the majority happens to work pretty well. From there, I moved into using some of the other tools, such as video face-swapping, attempting face-swapping with multiple faces, until I attempted their text-to-image generator to see how it'd work. (And also their image-to-anime generator.)

Of the other options, the video face-swapping is semi-decent, as it does its job relatively well, but it fails miserably when the face goes off-focus. The face-swapping app can capture anything that reasonably appears as a face, so you can use it for some interesting effects with a little, crude editing, but otherwise it can create something pretty disturbing.

As for the text-to-image generator, it's a mixed bag. From the prompts I managed to make, it's slightly better than the other options I've found. For one, it has produced the best mixed-race character prompt I've seen thus far, though it's still a little unresponsive to some prompts. One of the "benefits" is that you can use an AI optimization tool for the prompt, which basically makes it describe your prompt in simple language - which is ironic, as I was using prompting that would be easier to recognize by the TtI tool itself. Another benefit is that it lets you use different image generation engines (including Google's ones) to see how results would differ.

The main problem is that any tool other than the face-swapping is use-limited. Specifically, I couldn't get more than 2 or 3 videos overall, due to the duration restrictions, and even though they promise 6 prompts, you can only reliably get two before you get hounded into making an account. And the major problem is... there's no way to make an account. (I mean, you can try, but you get denied - unless you use your Google account, which I'm not very enthusiastic to.)

So, as a form of entertainment, it's a cool novelty. Image generation is a lot different from face-swapping, as one requires making a good prompt, while the other benefits from having most of the work done. But as a way to get the next best-selling novel? Yeah, it's better as a prompt generator than on the actual form of creation - and it's mostly the same for everything else. If I get a good image from one image generator, I could probably use a real photo model and a face-swapping app to refine it, and then maybe a third or fourth tool to do things like making a collage or do some editing in order to fix mistakes from the first few tools. And at some point, you start doing the work yourself and notice that they're great tools - but not enough to replace human creativity.

Anyways - more illustrations, please!