Type | |
Stats | 1,736 |
Reviews | (29) |
Published | Jun 23, 2023 |
Base Model | |
Training | Steps: 4,875 Epochs: 5 |
Trigger Words | Jorjon smiling soft smiling makeup full body |
Hash | AutoV2 7F0A0B4511 |
Join my new Discord here! https://discord.gg/cnVvnkgtPb
Jordyn Jones (Face & Body LoRA) - influencer, dancer, former OnlyFans model. This LoRA includes Jordyn's face AND body. Use the trigger words to get the desired result. Infinite Jordyn pics await you. (All images & models are prompted with 18+ descriptions & trained with 18+ models!)
Read Me!
TWO VERSIONS:
Jordyn Jones RHM v1: Trained on Real Hot Mix, my own mix. I use this LoRA for extremely high quality photorealistic results
For txt2img & img2img: LoRA weight between 0.9-1 for best results
Jordyn Jones SD1.5 v1: Trained on SD 1.5 base model, compatible with all models
For txt2img & img2img: LoRA weight between 0.5-1 depending on checkpoint model for best results (lower for anime/non-photorealistic models)
Recommended Settings
Hires fix: 0.2-0.3 for face, 0.2-0.4 for full body
Face is best at 1:1 resolution (make sure inpainting is 1:1 resolution)
Other resolutions work as well (see Training Info: resolution sizing for training dataset aspect ratio info)
'makeup' is a trigger word. Put it in negative to get Jordyn with no makeup (somewhat accurate)
SOMETIMES:
Jordyn may generate with a bunch of freckles/birthmarks. If this happens, you can put 'freckles' in negative and/or edit out the freckles using inpainting/photo editor
Photos may appear slightly picture perfect/oversaturated for outdoor prompts. If this happens, you can put '(oversaturated:1.5), (colorful:1.5)' in negative
Training Info
5 epochs, 25 repeats, 39 images
26 face, 13 full body pics
For resolution sizing, enable buckets = true (25 = 1 image)
bucket 0: resolution (384, 640), count: 50
bucket 1: resolution (384, 768), count: 25
bucket 2: resolution (448, 576), count: 150
bucket 3: resolution (448, 640), count: 25
bucket 4: resolution (448, 704), count: 150
bucket 5: resolution (512, 640), count: 225
bucket 6: resolution (576, 576), count: 350
Background
I've been experimenting with LoRA training and seem to have found a sweet spot for epic photoreal accuracy for people. I made Belle last week, now here's Jordyn. Best Jordyn LoRA on Civit!