santa hat
deerdeer nosedeer glow
Sign In
home
models
images
videos
posts
articles
bounties
tools
challenges
events
shop

Training FLUX Lora with Civit

driftjohnson
Grandfather Badge
Aug 17, 2024
training guide
Training FLUX Lora with Civit

Now we can train Lora with Flux Dev on Civit, through the website trainer, it's time to dive in:

Live at 3pm GMT 18/08/24

we have used the same dataset to compare training runs with different settings on Cascade and SDXL, now we turn attention to FLUX.

dataset used: https://github.com/MushroomFleet/assassinKahb-1024/tree/main

AssasinKahb Test Loras: https://civitai.com/models/654919

V1

AssassinKahb-Flux-512x-adamw8bit-e5.safetensors

  • Trained with the Civit Flux defaults (17/08/24)

V2

AssassinKahb-Flux-1024x-adamw8bit-e5.safetensors

  • Changed resolution to 1024 only, Civit Flux defaults (17/08/24)

V3

AssassinKahb-flux-1024x-Kappa-Prodigy-e12.safetensors

Ground Truth

dataset caption:

AssassinKahb style a demonic looking skeleton holding a sword with red hair 001

dataset example: AssassinKahb style a demonic looking skeleton holding a sword with red hair 001.png

V1

The results were actually very close to the ground truth, training was fast and the style has been learned well.

https://civitai.com/images/24761670

V2

Again, with 1024x as the set training dimension, we have learned the source material well.

https://civitai.com/images/24761997

V3

When we used Kappa's Config, it seems to have included some unique stylization and detail
https://civitai.com/images/24760468


Kappa Neuro's Config
{

"engine": "kohya", "unetLR": 0.0005, "clipSkip": 1, "loraType": "lora", "keepTokens": 0, "networkDim": 2, "numRepeats": 20, "resolution": 1024, "lrScheduler": "cosine", "minSnrGamma": 5, "noiseOffset": 0.1, "targetSteps": ????, "enableBucket": true, "networkAlpha": 16, "optimizerType": "Prodigy", "textEncoderLR": 0, "maxTrainEpochs": 12, "shuffleCaption": false, "trainBatchSize": 6, "flipAugmentation": false, "lrSchedulerNumCycles": 3

}

you can adjust your repeats or epochs.

(Image Count * Repeats * Epochs / Batch Size) = Steps

steps max out on civit at 10,000

https://docs.google.com/spreadsheets/d/1e4lFBh7XfS814RIWEvbuy-A0KAkzrXqEDTw2Fg9yNDs/edit?usp=sharing

to give you an idea ^^ LR Increase might be in order if you lower repeats and/or eopchs

The jury is still undecided on the best settings. Time will reveal them I am sure.
For now i present these findings as a way to see which approach might suit you.

Being able to train on Flux right now on Civit is amazing and prevents a lot of stress for people unable to run this on an expensive GPU !

Note: V1 & V2 used "append tags" where V3 does not.
V4 will be trained to show the effect of the append tags feature.

51

Comments