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.
Description
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
}
FAQ
Comments (5)
As mentioned in the description, I'd love to make a V2 of this one day with a larger dataset, but I'm struggling to find consistently high quality, photorealistic furries. If you know of any artists, directors, etc please let me know I'd be super appreciative. Ideally they are like Delken who uses means other than illustrious and thus avoids that muddy look on their images.
I have a pretty solid realism dataset you can use if you want. Problem is that it kind of has an almost 3d-cg look to it still even to know I think its pretty dang good. So it really depends on how realistic it needs to be. The detail level on fur and scales is next level though.
This image I recently posted "https://civitai.com/images/124534989" is a decent example of the level of detail the images have, although the proportions and style in this specific image aren't exact because I was playing around with styles.
I personally would love to see either a separate version for scales and skin type species, or a version of this that does not force only fur.
@willywizard That's nice. what model did you use on the image?
@Crft Tbh I used 2 models. The base was an experimental model I’m working on that I haven’t released, and a really low denoise upscale pass with ZIT.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.