A model of Freya, trained over 86 images for 1024 using Initium as a training model
Trigger word: gowfreya
Looks tags: brown eyes, long hair, brown hair, braid, arm tattoo
Weight: 1 is perfect
Outfit tags:
Trigger word
Tattered Witch Frock: freya_twf, armband, bracelet, sleeveless, jewelry, necklace, black shirt, brown leather vest, black pants, cloth belt
Agony's Promise Tunic: freya_fbt, brown tunic, sleeveless, belt around waist, gold belt, baggy pants, necklace, toeless legwear
Fate Breaker Tunic: freya_fbt, red tunic, sleeveless, belt around waist, gold belt, baggy pants, necklace, toeless legwear
Regal Vanir Garments: Freya_rvg, blue dress, red trim, leather sash, bandaged leg, anklet, pelt, sleeveless, olive knee-length pants, shoulder pads, black arm wrap
The Queen's Armor: Freya_tqa, gold chainmail, blue pauldrons, red Breastplate, black greaves, runestone belt, gold bracer, high collar, long sleeves, fishnet sleeves
Warrior's Battledress: freya_wbd, armor, buckle, black pants, brown shoulder armor, red bandaged leg, red bandaged arm, layered skirt, long sleeves, black gauntlets
If you wanna support me ko-fi
Additional information:
Webui I use
AAA Anime VAE SDXL v2 as VAE
Sampling method: Euler a
Schedule type I set it to Karras
Sampling steps I go 20-30
4xNomos8kDAT as an Upscaler
Hires steps I go 8-15 (I don't always use hires fix)
Denoising strength I go 0.4
Upscale by 1.2 to 2.0 depending on the starting image dimensions
Imagine dimensions vary depending on what I'm trying to do
I use 6 CFG Scale
uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face
Description
FAQ
Comments (2)
Somehow the sha256 checksum civitai displays doesn't match the checksum of the file, the lora works but the mismatch makes civitai helper extensions/nodes fail to process it properly.
First time I heard of anything like this, I don't know if there's anything I can do about it













