With this workflow, you can partially automate the testing of block weights in Flux LoRAs.
This is particularly interesting when trying to understand what the individual blocks are responsible for and what they control.
Once you know the single transformer blocks, it’s possible to train those exact blocks in Flux LoRAs.
The training then results in much more flexible LoRAs, as bleeding effects are reduced. Additionally, the LoRAs take up significantly less storage space, and training the single blocks is much faster compared to full LoRA training.
maDcaDDie has significantly improved the workflow and added a heatmap that makes it easier to see the changes.
https://civarchive.com/models/886270
Description
Works with Flux 1 Dev & Schnell
FAQ
Comments (9)
Mad props for this!
Did you do that manually? Respect for the work, thank you!
Thank you :)
You can copy paste Nodes, but i set all the "0" and "1" manualy ^^
do you think i could modify this for sdxl workflow? or maybe its faster to start from scratch... the amount of work you put into this is insane... and i kinda want something like this for sdxl.... but im too scared to even start