wavespeed-ai/flux-dev-lora-trainer

A blazing fast FLUX dev LoRA trainer for subjects and styles.

training

new

If True segmentation masks will be used in the weight the training loss. For people a face mask is used if possible.
If True, the training will be for a style. This will deactivate segmentation, captioning and will use trigger word instead. Use the trigger word to specify the style.
Specifies whether the input data is already in a processed format. When set to False (default), the system expects raw input where image files and their corresponding caption files share the same name (e.g., 'photo.jpg' and 'photo.txt'). Set to True if your data is already in a preprocessed format.

Idle

https://d2g64w682n9w0w.cloudfront.net/media/images/1746973386875408838_K41YWUQN.jpg

Your request will cost $2 per object,
For $1 you can run this model approximately 0 times.