This is my twenty-first style lora so go easy with me on this one. You can think of this one almost as much as a realism slider lora as a style lora. The "standard" weight I'd say this lora works best at is around 0.6. You can go lower than that if you want to bring in just a touch of realism, or move the weight up to 0.7 if you want to go all in. Anything more than that and you're playing with fire, but don't let that stop you from experimenting and reporting what works for you, I'd love to hear it. I also don't really recommend using this lora on top of realistic checkpoints like 3wolf at high weights, it won't look as good as you think. At higher weights you'll start to see artifacting and messy backgrounds. Simplifying your background and adding detailers is a must. For my sample pics, I tried to keep the checkpoints and levels of realism dynamic. Pick what works for you. For some reason Civitai doesn't display the weights I used for the lora but its mostly between 0.5 and 0.65. More info is in the workflows. Unfortunately only strictly furries are in the dataset. Scalies and avians will need to wait for a V2. It maybe can do those too but I wouldn't hold up hope. The reason the lora has "Delken" in the name is because that's the AI director who's images predominantly make up the dataset. I would love to have a more varied dataset but I haven't found anyone who consistently matches the quality Delken in pure realism IMO. If you have suggestions please DM me. I've always wanted to try and create a furry realism lora that is free from that "muddy" texture illustrious likes to give to the fur and hopefully this is just the first step. It's probably impossible but any hope of achieving that will need a much larger dataset. Delken if you're reading this, thanks for the awesome pics and sorry that I stole them. Feel free to DM me if you want the name taken off the lora or for anything else.

Delken Furry Realism Enhancer

Trained on 146 images: { "engine": "kohya", "unetLR": 0.0005, "clipSkip": 2, "loraType": "lora", "keepTokens": 1, "networkDim": 16, "numRepeats": 7, "resolution": 1024, "lrScheduler": "cosine", "minSnrGamma": 5, "noiseOffset": 0.1, "targetSteps": 5110, "enableBucket": true, "networkAlpha": 8, "optimizerType": "Prodigy", "textEncoderLR": 0.00005, "maxTrainEpochs": 20, "shuffleCaption": true, "trainBatchSize": 4, "flipAugmentation": true, "lrSchedulerNumCycles": 3}

Files with SHA256: bd1f9ccde31bc8a07ef118002e431b45473008932a3308651f50092286970cf5