Granted its still in production phase but despite that I still can say this is it! I did not like how mid journey and the other online only webapps. In general I dislike all web apps because they're web apps and subscription licenses. Locally hosted buy once is the way to go. Ai Image generation is interesting and fun. Getting the settings and prompts to generate with precision is tough. Not just your software but all AI generation services. Learning properly has been slow going. Your software offers a lot of options and that's a huge bonus. Get this software more polished and you could sell this with a higher price tag. Id be willing to pay the difference, as long as the higher price is within reason of course. Also I understand "polished" as a goal is vague but it gets the idea across. Mostly I mean functionality and user friendly, bugs can be fixed with updates and I wouldn't expect these updates to include trying to keep up with major advances in the AI image generation world.
Mostly I just wanted to give you my thanks for this. And offer a couple suggestions. First suggestion is a zoom in and zoom out feature. If that exists already I couldn't find it and if so please point me in the right direction. Next is a user manual. That in itself is a huge project. I can understand it's a task that you might not get to for a while but it would be helpful for me and people like me. I'm sure you're a busy person and you have your priorities, just throwing it out there. The zoom feature might be an easier task, especially if its already implemented.
to learn what everything does, I'm having to just play around and try things out. I've used other AI image generators so i'm not completely in the dark about what to do. Sometimes I get some good images, impressive actually, others its not even close. The problem is entirely on the user end because I don't know really how to use a lot of these settings. I know that some models matched with schedulers will be good for some prompts but not others. I've been looking around online to try and get a clue but most descriptions are metaphorical and no help at all. I'm not even sure if these people are trying to dumb it down for people like me or if its that they don't even understand it really.
The pix2pix, inpaint/outpaint could be really awesome for me. I'm something of a digital artist or at least aspire to be one and if i'm looking for idea generation this would be golden. Again I'm not sure about configurations and all that. Every try is a shot in the dark so of course I'm not getting the kind of results Id like. I've not even txt2vid yet, I'm afraid the results will give me nightmare fuel. I could type in a prompt "puppies playing in the dirt" and id get a video of "piles of partially liquidated, horribly mutated puppies on dirt".
I am having fun just messing around trying things out. Sometimes it works and it works fantastic.
Oh maybe you know of a good site or more that would help me understand more about what these various settings do. The prompting part I've got a good grasp on, at least how it worked on Mid journey and Leonardo, but if AI runner does it differently and you know where I can learn more please point me in the direction. I'm slow learner but if its quality info I'll manage to figure it out eventually. Thanks.
One last thing, will AI runner have any updates in the near future? Everything runs fine, Just updates are always fun. Unless its coming from Microsoft or google....they're updates are nonstop and frequent..its annoying.