This version is now trained on 1000 high detail and high resolution images of Women, Men, Animals and Macrophotography altogether.
Best outputs are after upscaling, as the details really start to shine with 1.5-2x upscale.
i personally used full strength on the model, but everything from 0.5-1 and 30-60 steps makes a difference already.
Be aware, apart from upscaling, all provided images are only txt2img, so minor issues are sometimes visible.
For now this will be the last detailer update for SDXL and once SD3 will be updated and ready for loras, I will update this with the same dataset.
As always, id love to hear your feedback and ideas for improvement.
Training parameters:
{
"unetLR": 0.0005,
"clipSkip": 1,
"loraType": "lora",
"keepTokens": 0,
"networkDim": 32,
"numRepeats": 1,
"resolution": 1024,
"lrScheduler": "cosine_with_restarts",
"minSnrGamma": 5,
"noiseOffset": 0.1,
"targetSteps": 5000,
"enableBucket": true,
"networkAlpha": 16,
"optimizerType": "Adafactor",
"textEncoderLR": 0.00005,
"maxTrainEpochs": 20,
"shuffleCaption": false,
"trainBatchSize": 4,
"flipAugmentation": false,
"lrSchedulerNumCycles": 3
}
