Recommended settings (v7-v8):
Steps: 16+CFG scale: 2.5+Note - This checkpoint is capable of generating decent results with just 8-10 sampling steps (recommended settings: Sampler – DPM++ 2M Karras, CFG Scale – 2.5). Because of this, there is no need to use the SDXL Lightning LoRA, which is also not highly compatible with this model.
Positive Prompt
[unholy-aesthetic (OR) unholy-detailing] <-(Optional),masterpiece,best quality,amazing quality,very aesthetic,absurdres,ultra detailed face,ultra detailed eyes, Negative Prompt
bad quality,worst quality,worst detail,sketch,censor, extra limbs, deformed fingers, bad anatomy, mutated body, lowres, worst quality, low quality, low score, bad score, blurry, text, ugly, hooded eyes, watermark, pale, bad hands, bad anatomy, bad proportions, poorly drawn face, poorly drawn hand, missing finger, extra limbs, blurry, pixelated, distorted, lowres, jpeg artifacts, watermark, signature, text, (deformed:1.5), (bad hand:1.3), overexposed, underexposed, censored, mutated, extra finger, cloned face, bad eyes,Recommended settings (v6):
Steps: 40+CFG scale: 7+Negative Prompt
lowres, worst quality, low quality, low score, bad score, blurry, text, ugly, hooded eyes, watermark, pale, bad hands, bad anatomy, bad proportions, poorly drawn face, poorly drawn hand, missing finger, extra limbs, blurry, pixelated, distorted, lowres, jpeg artifacts, watermark, signature, text, (deformed:1.5), (bad hand:1.3), overexposed, underexposed, censored, mutated, extra finger, cloned face, bad eyes,🔥 Unholy Desire Mix - Sinister Aesthetic (ILLUSTRIOUS) v5 is Now Online
Previous version Online Generator - https://tensor.art/models/835952257007743162/Unholy-Desire-Mix-Sinister-Aesthetic-(Illustrious)-v1.0
Positive Prompt
unholy-aesthetic <-(Optional),masterpiece,best quality,amazing quality,very aesthetic,absurdres,ultra detailed face,ultra detailed eyes, Negative Prompt
bad quality,worst quality,worst detail,sketch,censor,Recommended settings:
Steps: 25-40CFG scale: 5-7Sampler: Euler a Working with and without Keyword "unholy-aesthetic"
Conclusion
Use Keyword "unholy-aesthetic" for post processing, additional background detail or colour adjustments (Note – depending on the amount of detail / environment in an image, It may or may not work.) e.g. -
Description
FAQ
Comments (22)
It seems that v6 is much worse than v5 when it comes to feet. With v5 you can get the correct amount of toes really quick while it took me a ridicioulosly high amount of tries to get one picture with the correct amount of toes with v6.
I think i also like v5 generally more, but for that statement i need to do more testing with both versions.
Edit: Yes i like v5 more.
Yes, I like v5 more too. v6 has been a downgrade in every regard except the 3D aspect.
Thank you for the exchange
So far V6 seems to nail lighting way better and leans more towards a realistic style. That said, it struggles with smaller details like fingers. I think i will stick with V5 for the time being.
V5+Dramatic light ill LORA is better
GOAT
V6 always gen the character too young and very hard to move the hair bang
good
Wait a second this is a curated gallery, 🤣 Well, beauty is in the eye of the beholder as they say...
Take it back
V6 failed with less known characters compared to V5.
Sometimes I get some really beautiful results with this one. Some great alternative which should get mor attention.
Edit: But sometimes, combining it with some loras, I get some really weird monsters appearing
Would it be possible for you to remove NSFW images from Tensor posts?
Due to the change in specifications, if there are images with blur settings, the model is more likely to result in a 404 error and become unusable.
https://tensor.art/models/835952257007743162
done
I'm a HUGE fan of this model. Been using v5 and v6 a lot locally. Both are rgeat models, pure magic, with great details.
But there is a problem with v6: it generates characters too young, even with tags like 'adult' or 'aged up', which for me personally is a bad thing; v5 is much more reliable for generating not too young/young characters. But for any other characteristic, v6 is a great improvement. Hope the 'loli' problem can be fixed in possible future versions.
谢谢你的分享；如果加上成年人类的描述词，loli现象能不能改善
The most recent version of this model is uploaded to Tensor?
I think so……The characters' body movements in version V5 are more refined, and the art style is more serious, with less saturation. It is suitable for creating serious and sorrowful works.
The V6 version has greatly improved lighting quality, with exquisite character lighting, better hair and fur details, and beautiful hair. It's a dreamlike illustration. I'm willing to put up with the V6 version drawing a few extra fingers.
V6 makes a huge 13 gb model if merged into anything.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.