Experimenting with training a character LoRA starting from one image. Inspired by https://civarchive.com/articles/3021/one-image-is-all-you-need
{
"unetLR": 0.0005,
"clipSkip": 1,
"loraType": "lora",
"keepTokens": 1,
"networkDim": 64,
"numRepeats": 20,
"resolution": 1024,
"lrScheduler": "cosine",
"minSnrGamma": 5,
"noiseOffset": 0.1,
"targetSteps": 1400,
"enableBucket": true,
"networkAlpha": 32,
"optimizerType": "Prodigy",
"textEncoderLR": 0.00005,
"maxTrainEpochs": 20,
"shuffleCaption": true,
"trainBatchSize": 8,
"flipAugmentation": false,
"lrSchedulerNumCycles": 3
}
Description
FAQ
Comments (4)
can you post some examples of how it works?
that's the plan
@WhiskyBoat damn it works perfectly! even in weird perspectives with a strength of 1!
@Telekinetic_tomato I'm pretty impressed with how flexible it can be, especially with all the excellent LoRAs available these days.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.