These "strong style" Models are intended to be merged with each other and any model for Stable Diffusion 2.1
I recommend merging with 0.5 (50/50 blend) then using prompt weighting to control the Aesthetic gradient.
example merged model prompt with automatic1111:
(GrimKnights:1.2) (yourmodeltoken:0.8)
if you drop the "djz" and the "V21" what remains is the token you need to call up the concept in the model. All examples shown were the Raw Token, no other words. Tokens are case sensitive and in almost all models it will match the filename.
It is possible to merge these models with each other using a different value. It is possible to pair models and then merge those resulting models. In this way we can blend abstract concepts together and then weight the tokens to achieve the result we may wish to create. Of course to eliminate all those tokens, you can simply train a new custom model from the outputs, which means you are back to a single token.
A video explanation will follow, but for now the above explanation should do. We are focused on getting as many style/aesthetic models into artist hands to enhance the creativity already at their finger tips.
Art Freedom for all!!
[all original artwork used for training with full permission from Drift Johnson]
Description
FAQ
Comments (10)
i downloaded the file added it to my models and got the usual error when missing the yaml file. since the base model is SD 2.1 768 i used the file from the base model.
now i get a ton of errors.
looks like i am to stupid to install ur checkpoint.
any tips you can give?
No problems, our group has used this model a bunch this month, so we know it does work. We will add the config we are using for this model tonight. Expect a follow up comment here soon.
We confirmed this is working, and I have added the config we are using, which is tested working with Automatic1111 webUI on 29th January 2022
We wrote up a Question & Answer for you, as other ask this same question a lot:
https://civitai.com/questions/116/sd-2021-model-wont-load-config-yaml-files
Make sure the filename of the .yaml we supplied matched the filename of the model you downloaded :)
comment back if you still can't figure it out, there are more things you can try.
i just want to kiss you! thank you so much
ok, so the model is loading but my happiness was a tad bit early. when i run any prompt i get the following error:
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.
sry for "spamming"
using --disable-nan-check the model loads and runs, the output is only black pictures tho
@Whinegummi consider "--xformers" instead of "--no-half" as your launch args
let me know how you get on :)
@Whinegummi i have never used "--disable-nan-check" but i do use "--medvram --xformers --opt-split-attention" so of course it depends what GPU you are running, but you could try this too :)
@axsthxticroot xformers did the trick, cant tell you how happy you made me
@Whinegummi Glad you got it all working :D :D !!
Details
Files
djzGrimKnightsV21_0.yaml
Mirrors
illuminatidiffusion_v1.1.yaml
Old_Portraits.yaml
SD2.1_MilfShaper_v1.0(FP16).yaml
KitchenSink2nsfw.yaml
AllureAI_batch4_v03-ep220.yaml
CharHelper_v2_ SDv2_1_768_step_8500.yaml
CharHelperV3.yaml
SDArt_AliceInDiffusionLand768.yaml
oxigien_v20_lite.yaml
oxigien_v20_ultra.yaml
SDArt_synesthesia768.yaml
woolitize-SD2.1-768px.yaml
ArtiusV2.1.yaml
KitchenSink2safeFP16.yaml
PXL8V1.yaml
KitchenSinkVer1.8L.yaml
pulp-diffusion.yaml
sticker-v1.yaml
UltraCmodel.yaml
yai-2.2.14.yaml
yai-2.2.20-F.yaml
vector-art.yaml
djzGrimKnightsV21_0.yaml
oxigien_v20_Lite.yaml
Mangled_Merge_V3.yaml
ZphyrRemember.yaml
oxigien_v20_Epic.yaml
dragonportrait-sd21-768-v1.yaml
concept-sheet.yaml
djzInkPunkV21.yaml
comodel2.yaml
food_crit-SD2.1-768px.yaml
pulp-vector.yaml
wd15-beta2-halo-aesthetic.yaml
graphic-art.yaml
graphic-art-1_1.yaml
ZphyrInsanity.yaml
SDArt_UnmythicalCreatures768.yaml
CharHelper_v1_ SDv2_1_768_step_3500.yaml
CharHelperV4.yaml
CharHelper Fine-Tuned.yaml
SDArt_Encapsulated768.yaml
URPM_2.1_V2.yaml
perpetual-v1-moon.yaml
URPM_2.1_V1.yaml
rMadaSD21_v6.yaml
macarolus2.yaml
SDArt_CosmicHorrors768.yaml
ZphyrPortraits.yaml
realismEngine_v10.yaml
pretty_girls_next_door_v2.yaml
pretty-girls-next-door-v5.1.yaml
pretty_girls_next_door_v6.0.yaml
KitchenSink2safe.yaml
dragonportrait-sd21-768-v2.yaml
KitchenSinkVer1.8.yaml
PRMJ.yaml
3DMDT1.yaml
yai-2.2.14.yaml
yai2.2.20.yaml
yai2.2.20.yaml
Ushio_Anime_V1.yaml
Cthugha.yaml
ultraskin.yaml
PseudoFreedomMerge.yaml
naturitize-SD2.1-768px.yaml
djzDivineStatueV21.yaml
clayitization-SD2.1-768px.yaml
pretty_girls_next_door_v9_0.yaml
wooditize-SD2.1-768px.yaml
A-to-Zovya_RPG_Artist_Tools_21_V1.yaml
wd-beta3-base-fp16.yaml
classicnegative768px-v0.2.yaml
YAI2.3.22.yaml
imagineV41_v10.yaml
BoW-config.yaml
SDArt_v1.yaml
SDArt_v2_768.yaml
pretty-girls-next-door-v1.yaml
Mangled_Merge_V2.yaml
SDArt_ChaosAndOrder768.yaml
pretty_girls_next_door_v7_0.yaml
pretty_girls_next_door_v8_0.safetensors.yaml
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















