Download
1 variant available
552
4.4K
37.3K
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.
![00063-[number]-lcsrts gamestyle with menu on the bottom of the screen. a caped villian, dressed like a red Batman, is holding a pistol and int.png](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/17582907-2b2d-4bd8-8b0e-686780f4812b/anim=false,width=450,optimized=true/00063-[number]-lcsrts gamestyle with menu on the bottom of the screen. a caped villian, dressed like a red Batman, is holding a pistol and int.jpeg)
Trigger is "lcsrts gamestyle"
This was an old attempt I did to train a LoRA for Flux that could recreate the style of 80s/90s LucasArts point & click adventure games INCLUDING the lower thirds menu (w/ text options and inventory). It -almost- turned out. I ran training sessions of it a few times w/ tons of steps and various datasets but it never 100% got the text right/include the menu every single generation as I was hoping it would.
Anyway, it's been sitting on my HD for 3 months now so I'm just going to post it for anyone who wants to play around w/ this style. With proper prompting/workflow it can definitely produce great LucasArts style images, but it's just too inconsistent for me to be super happy about. Soooo use at your own risk and don't dog me :)