Verified: a month ago
SafeTensor
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
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.