UPDATE: safetensor(float 16) and Pruned version file for PastelMixAlike
New Version: PastelMixSam
This version has SamDoesArts LoRa embedded in it.
NOTE: If you're using PNG info from my old sample(Delete the old hash from "Override settings" as it disables the embedded LoRa and uses only the model.
UPDATE: After testing, I have concluded that PastelMixSam yield the same result as PastelMixAlike. Just remember to delete the hashes when copying model hashes from PNG info and you're all good.
And Trigger Word is not necessary for both versions. The result will change, for the better or worse (They all look good)
A new version is coming that will enhance the THICC and sexiness of the body. Stay tuned!
PastelMixAlike
Just my fine-tuned version of PastelMix
No vae is needed but nai.vae is the only vae that i think that are somewhat decent here.
Clip skip=2 and "quantization in K samplers" is enabled
Several Lora was used to test its compatibility:
SamDoesArts (Sam Yang) Style LoRA as the Base Lora:
https://civarchive.com/models/6638/samdoesarts-sam-yang-style-lora
Compatible well with these Lora: (Need some prompt tuning)
Recommended settings are included within Sample images
Currently, there are purple artifacts that are affecting images. If anybody has a fix please comment down below.
Description
New Version: Delete the old hash from "Override settings" as it disable the embedded LoRa and uses only the model.
FAQ
Comments (19)
.ckpt version produces nice images like on those examples, but .safetensors isn't working properly (and it's about 1.5G smaller, too) - probably something went wrong during format conversion
Confirmed. Deleted it for now
Fixed
Very confusing, so i want the latest ver, to be able to reproduce the images you have shown. Which is it PastelMixSam? or PastelMixAlike? i want the model that has the lora embedded within it. Great images btw hoping to achieve the same!
PastelMixSam is the version with the embedded LoRA
@DegenerateAkko Thank you very much! downloading now!
@vitherenegade Also remember to delete the hashes when copying info from png info(if the result is incorrect). Sometimes I even forgot to do it
what is diference between alike and sam version ?
almost nothing other than you don't need to use the base LoRa
I wasn't able to get results similar to what you showcased even though I used the exact same prompt and setting.
Have you disable the hash model. If you copy my images using PNG info. There will be a model hash that needs to be deleted. Have you download the Samdoesart LoRa. If not you can use the PastelMixSam version instead which have the LoRa built in
Can't seem to find the nai VAE you mentioned, could someone link it? because i've been sitting here for hours trying to find it
@DegenerateAkko thanks man
GOOD GOD CAN SOMEONE PLEASE TEST THE MODELS FOR SOMETHING OTHER THAN SEXY BABES. WE'D LIKE SAMPLES OF OTHER THINGS.
theres a hamster in space...
lmao no we wouldn't
Will you update this for sdxl when it releases? It's probably my favorite checkpoint, it'd be awesome to continue to use it
wow
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.