Flux
Rome Flynn.. All sample images are with no face detailer or hi-res fix, they are 1024x1024 resolution. They are generated on Euler at 20 steps. This lora is trained on 1024x1024 resolution as well. I used flux dev in the sample images.. I've done testing and there are 2 ways my loras usually work best:
Strength at 0.9-1 with no trigger word
Strength at 0.85-.0.95 with trigger word: r0m3
i use comfy ui and theres a strength_clip option in the lora node and i set it to 0.85. Idk whats best but thats what i do
SD 1.5
Trained on 768 resolution. This works with mostly realistic checkpoints like the other sd 1.5 Loras I made I tested a flexible one with this one but I feel this one was better. Strength 0.9-1. Here is the checkpoint I recommend using: https://civarchive.com/models/462596/photonic-fusion
Other one I recommend but don't think works as well with it: https://civarchive.com/models/386205?modelVersionId=430987
SDXL
An actor
Strength at 0.9-1,
put this in negative prompt: ugly, deformed, airbrushed, photoshop, rendered, (multiple people), blurry, child, mouth open, teeth
Here is a photo of him: