The LoRA was trained on Flux-Dev.It also works with Flux-Schnell, but I behaves slightly differently.The showcase images are made with Flux-Dev.For Flux Dev I recommend the following setting - Lora strength 0.7 - 0.8 greatly depending on the image, highres fix with denoising 0.3I didn't test it much with Flux-Schnell, but I noticed you get better results with 8-10 steps rather then the usual 4
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
Thomas Blackshear - V1
Taste of Taiwan - Oyster Thin Noodles v1.0
Ferrari SF90 XX Stradale - 2024 - v1.0 FLUX
Most Important Places - Thank You Special - Last Night
![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
Dreamy and Colorful - v1.0
High Braid Pony Tail - v1.0
Robert Sammelin - V1
Jessica Keynes, Ladybug, Miraculous. Different models and attires. - Civilian (Flux)
Defaced - V1
Ashley Wood - V1
Bookish - V1