Video
Flux LoRA training video:
https://youtu.be/DGjvHTrrgu0
Generation Settings
use LoRA weight 0.7
with trigger word: rpm@milliegibs0n
sampler: Euler
scheduler: simple
steps: 20
Hires.fix:
upscaler 4xFFHQDAT, steps 5, denoising 0.3
my testing for generating images was done with Flux 1 Dev
Mixing LoRA's
works well with Sony Mavica MVC-FD7 LoRA for realistic generations, used at 0.3 weight:
https://civarchive.com/models/1147127/sony-mavica-mvc-fd7-real-digicam
you can try mixing LoRAs, note that in my testing mixing the same concepts (like body or face) above 100% didn't work well (e.g. 0.7 + 0.3 is 100%)
Attribution
This LoRA is trained on the FLUX.1 [dev] model by Black Forest Labs, Inc., licensed under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs, Inc. For full license terms, see: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
Description
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.