Download
1 variant available
fp16 PickleTensor
kda_all_out_evelynn_nai_mix_12000.ckpt
Half precision, best balance • 3.82 GB
Verified: 4 years ago
This asset is only available as a PickleTensor which is a deprecated and insecure format. We caution against using this asset until it can be converted to the modern SafeTensor format.
This is what the original model was trained on. Will produce the most accurate Evelynn & is good for mixing

7530 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
8.8K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
K/DA All Out Evelynn
Default download set to LORA model
(I accidentally uploaded the wrong version, it should be fixed now)
How to use
This is a LORA model which means that you will need https://github.com/kohya-ss/sd-webui-additional-networks to combine the LORA with any model of your choosing.
Generating example images
I'm using AOMV2 and anythingv3.
Alternative downloads
Alternative downloads were trained via dreambooth
Model Variants
Creating your own variant
Grab a model from anywhere & go to "Checkpoint Merger" in web-ui. Set A to the downloaded model. Set C to the original model. Set B to the model you want to add it to. Set a custom name, multiplier to 1, select "add difference". Save as fp16 to save space.
