Similar training parameters to v1 except I used constant instead of cosine_with_restarts and stopped at epoch 17 - The resulting LoRA produces images more inline with my intention. Seems easier to get results with simple prompts.
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
Milo Manara - V1
Sergey Kolesov - V1
ta86_neonmythos - Flux_V1
Terry & Rachel Dodson - V1
Dreamy and Colorful - v1.0
Sausage Dishes - White Sausage-Dev v1.0
Waldemar von Kozak - V1
Mgrt03 - V1
Jaguar XJ220 -1992 - v1.0 FLUX
Free for Premium Users
ModelsLab
Flux.2 Dev Text to Image
Underflowered - V1
![Gamebook illustration [Flux + IL] - Flux](https://images.modelslab.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a3d7d0f8-2b1d-4248-ba54-c5406ffca31f/width=832/100131022.jpeg)
Gamebook illustration [Flux + IL] - Flux