Reply to thread

Message: <blockquote data-quote="VHawkwinter" data-source="post: 9884858" data-attributes="member: 7040136">Just FYI, that is because you're using cloud services to do it.The process you're describing is doable right already if you are running some model on your own videocard with sufficient RAM. From your comments about this workflow, I assumed that was what you were doing.Running some model on your prompt on your own hardware; and then feeding it back in and doing many image to image changes masking our different areas; exporting it to an image editor and doing partial edits of your own, and then feeding it back in and doing image to image changes with masking so only certain parts of hte image are changed, etc. I don't know exactly what the tools look like now, but I'm sure the software is more fleshed out than when Stable Diffusion was new and I tried running it on my videocard through a Python app I found online to see what it was. It's not a hypothetical, it just requires you to use your own hardware.I assume companies with their own customised models running on art they own (Say, Hasbro having fine-tuned some model or other on MtG and D&D art {I don't know if there are any contractual terms that would prevent them from doing so, for the sake of this argument I am assuming not}) are doing something like that, and having their employees connect to a server with a GPU adding jobs to a queue, not connecting to an external cloud service.</blockquote>