I created this model to supplement missing box art for games in my LaunchBox collection.

Trained on 75 images. I am still figuring out the in's and out's of Lora training but I believe this one turned out well.

I would suggest running it 1 -1.5 strength. Crank it up if its not getting the angle right but you should be good with 1 strength if you prompt it correctly as shown below.

There are a bunch of triggers but the most useful ones are (atari 5200 box,angled view,copyright name) at the beginning.

A prompt formula that works well is : trigger words,(insert scene here),(insert style here),(insert title you want on the box if any)

EXAMPLE PROMPT:

atari 5200 box,angled view,copyright name,a side view of a cat standing on its hind legs fighting with godzilla,retro artsyle,title at the top says GODZILLA VS MEOWSER in red letters

It will probably take a few tries to land perfect text. I can never get it to land the text on the spine right so that may require some external editing if you really want it.

I used a few text detailers with mixed results.