Sally Whitemane is on NoobAI-XL (V-pred / Epsilon), Pony and SD1.5 now!
High Inquisitor of Scarlet Crusade Sally Whitemane!
Note about NoobAI-XL V-pred:
Check my guide about V-pred image generating!
The best model to use V-pred is Cyberfix! But pure NoobAI-XL V-pred is also good
PonyXL / NoobAI-XL tags:
Main tags:
Sally Whitemane, 1girl, mature female,
white hair, red eyes, makeup, lipstick, red lips,
hat, shoulder armor, high collar, multiple cloaks, pelvic curtain, two-tone leotard, elbow gloves, thigh boots,
optional: holding staff, no headwear, red thighhighs, red gloves
Partners for interactions:
orc, green skin, interspecies
troll \(warcraft\), blue skin, tusks, interspecies
tauren with hooves, horns, furry male, furry with non-furry, interspecies
werewolf, furry male, furry with non-furry, interspecies
Sylvanas Windrunner, elf, pointy ears
NoobAI-XL quality settings:
Put "masterpiece, best quality, good quality" in positive and put "low quality, worst quality" in negative.
Use euler, cfg 4-5. Don't use higher CFG!
If you have over-constrasted picture and cfg 4-5 didn't help you can try to put in negative "colorful".
PonyDiffusion v6 (XL) settings:
Style settings for PonyXL (very important):
score_9, score_8_up, score_7_up, score_6_up, score_5_up,
Use 3D in positive or negative for 3D arts / anime arts.
Negative prompt for PonyXL (recommended):
censored, blurry, head out of frame, watermark, jpeg artifacts, muscular female
Also add in negative annoying objects.
Recommended negative - if you want to remove hat use in negative "(hat, red headwear:1.1)" because Sally Whitemane has "baked-in" hat in PonyDiffusion V6.
SD 1.5 character tags:
SallyWhitemane, 1girl, mature female, holding, staff,
white hair, long hair, red eyes, jewelry, black eyeshadow,
hat, shoulder armor, elbow gloves), two-tone leotard, pelvic curtain, thigh boots, gold trim,
recommended negative prompt (for preventing double staffs, cloth in hand and for hiding groin by leotard not by pelvic curtain):
bottomless, groin, dual wielding, towel
Please don't forget rate my LoRA. This motivates me to do more!
Upscaler / adetailer settings:
Hires.fix: Upscaler foolhardy_remacri (download and put in "ESRGAN" folder in "models" if you are using automatic1111 or forge).
Hires steps: 16-18
Denoising strength: 0.3
Adetailer: denoising strength 0.3. Detection model confident threshhold: 0.7-0.8.
Best sampling method is euler / euler a, 25-40 sampling steps, You don't need any DPM++
Description
FAQ
Comments (5)
Works very well, gj.
Hey ho, i have a "problem". For some reason i cant tag your amazing lora in my image. How can i fix that?
Hello. You need to use https://github.com/civitai/sd_civitai_extension in your Stable Diffusion webui (Can be installed manually in install from URL tab in extensions). If you already have it - delete safetensor file with LoRA, json and preview jpg with the same name in LoRA folder, download again and restart your webui (Also you can push apply and restart in extension tab). These actions will allow the extension to re-assign the hash number to the LoRA and the site will recognize it.
I have the same problem with all my old LoRAs and old LoRAs made by other people. I don't understand what cause this problem (maybe Automatic1111 updates) but the only solution - delete LoRA, json file, preview, download again, restart Automatic1111 and it will work.
If you already have art you can reassign hash in img2img - inpaint (only mask) by little changes in small area with the same prompt or you can just generate again your art with hash-updated LoRA in txt2img with the same settings and seed (if you already fixed it - img2img inpaint method is preferrable).
Also you can manually upload image in gallery section (add post or add review). This will force the image to be linked to the LoRA model, regardless of the hash. But if you have multiple models used and you want to cross-post everywhere, you need to follow the previous instructions.
@Enigmata Oh i see, Yeah i dont want to spam with same (like SAME SAME) images but next time ill be sure to do things a right way.