The beggining of a great project !
Note : don't generate BELOW the base resolution (768*768)
Providence - Prelude
A precise chosen noise offset setting
A large variety of subjects, I took care to to keep the flavour at maximum from genesis seeds feel
No baked VAE (works fine without any tbh)
Hyper Realism
For good results please use the forAnalogPortrait negative embedding.
Digital painting
For my digital painting finetune, please use “character portrait” along “digital painting” for enhance the quality
Analog
use the forAnalogPortrait negative embedding aswell.
Troubleshoot :
NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
A 2.1 model require either --xformers and / or --no-half start argument from the webui-user.bat
set COMMANDLINE_ARGS= --no-half --xformers
check also if your config file is named correctly alongside the model

Happy tuning !
romerorz.art - Twitter - DeviantArt - Gumroad
Description
Painting adjustements
FAQ
Comments (7)
The download link of config files for 1.1 and 1.2 are 404 for me. but the link to 1.0 works fine. Not sure if this is an issue with citivai itself.
The .yaml configuration file is empty for versions 1.2 and 1.1. I had to download the one for version 1.0 "Prelude", and although the results are not exact, at least there is no error when trying to load the model.
Thoses config download issue are kinda weird, I tried it and I got a correct one providence_2112Anchor.yaml of around 1.83 kb
@romerorz I see you updated it 4 hours ago but still not fixed for me :( Some civitai problem, I assume. Would manually editing some paremeters in the old file work?
@laurancio All config files are identical for 2.1 models, it should work without issue, what errors are you getting ?
@romerorz Ah, okay, and yeah, it does work, I just assumed they might be slighlty different and somehow give different results. But if not, then there's no problem! Thanks for answering so fast
Getting this error?
"Error: Could not load the stable-diffusion model! Reason: Cannot copy out of meta tensor; no data!"
How do I fix it please?
Details
Files
providence_2112Anchor.yaml
Mirrors
Tilt Shift LoHa.yaml
ffusionAISD21_768BaseAlpha.yaml
idle_Potion_Generator.yaml
F1 LM-000004.yaml
coloringBook_coloringBook.yaml
c5x7-21-v01.yaml
Speedtail-000002.yaml
Orc_reg_128.yaml
Amg One.yaml
Countach lp800.yaml
CitroenC6-21-v1.yaml
providence_2112Anchor.yaml
allworkforkrowk_v02GammaFasterlr512.yaml
AnyTayJoy-woman_Vparam_Reged.yaml
evo_car_D-adaptation-LoRA_SD21-768_v044.yaml
ffusionAISD21_baseV100.yaml
evo_car-dm_plaza_D-adaptation-LoRA_SD21-768_v045.yaml
providence_2111Anchor.yaml
Speedtail-000004.yaml
evo-car-lora-sd21-768_v02.yaml
shurima-1-000010.yaml
providence_2110Prelude.yaml
gdsingld.yaml
Aston Martin DBX Interior-000002.yaml
LBWK360MODENA-000001.yaml
m14af1car70s.yaml
drccitycar_v0.3.yaml
Rx7FD-000002.yaml
Speedtail-000001.yaml
Aston Martin DBX-000002.yaml
anime21_v15.yaml
Aston Martin DBX-000001.yaml
Rx7FD-000001.yaml
pixhell_v20.yaml
mcaf1car70s.yaml
DaveScare-v2.yaml
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.

















