[Kootle]

Best way to deal with the sense of doom imo is to actually use it. You'll find how dumb it really is by itself, and how much of your own judgment/help/editing is still necessary to get anything usable. It might look like magic from these manicured press releases, but once you get your hands on it, it quickly becomes just another tool in your toolbox that, at best, helps you do the work you were doing anyway, more quickly.

[teaearlgraycold]

I work with these models professionally (well, I’m a web dev working along side people manipulating these models). When you give it a prompt and it spits out a pretty image, remember that the range of acceptable outputs is very large in that context. It demos very well but it’s not useful outside of stock image/stock video use cases. What artists and engineers actually do is work under a rigorous set of constraints. Getting these models to do a very specific thing, correctly adhere to those constraints, and still maintain photorealism (or whatever style you need) is a very much unsolved problem. In that case the range of valid outputs is relatively tiny.