Second attempt at training for FLUX, it still doesn't produce the expected results.
It would be good if CivitAI made a LoRA training article on how to get the best out of training because testing is slow and not cheap.
I suspect the issue is with the image captioning that needs to be done differently to SD models.
It's supposed to look like this SDXL and PONY versions.
Version Detail
FLUX.1
Project Permissions
Use in TENSOR Online
As a online training base model on TENSOR
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges
Commercial Use
Related Posts
Describe the image you want to generate, then press Enter to send.