Trained on 19 images. Mostly picked from the in-game cut-scenes so that I could eliminate any HUD elements and not have the screenshots include any one particular subject. I used minimal natural language captioning that I typed myself. I'd like to work on training a v2 in the future with a better dataset and better captions. v1 is more of an experiment. I'd recommend a strength of 1.5 to 1.9 for decent in-game looking results. Trained using fluxgym with a learning rate of 1.5e-4. Using the article by CrasH for guidance.
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Idle
Unknown content type
Related Models
Discover similar models you might be interested in
Dewy skin - v1.0
Jessica Keynes, Ladybug, Miraculous. Different models and attires. - Civilian (Flux)
fantasy-tree - v1.0
ta86_neonmythos - Flux_V1
Candy | Cute and Fun - v1.0
Sausage Dishes - White Sausage-Dev v1.0
Waldemar von Kozak - V1
Most Important Places - Thank You Special - Last Night
Dreamy and Colorful - v1.0
Most Important Places - Thank You Special - Thank You Special v1
Magical Mass Style - v1.0
Mgrt03 - V1