Corrects anatomical errors when creating vertical images, increases color vibrancy without losing the necessary darkness, more realistic lighting and shadows, more diverse images
If you like my content, support me at:
Patreon in here:
https://linktr.ee/Duc_Haiten
If you want to use my models to create unlimited images at a small cost without having to install anything, mage.space will be a good choice, i have some models that are exclusively available on there.
Activation keyword not required
Negative prompt:
(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, cropped, extra limb, missing limbs, deformed hands, long neck, long body, signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist
Description
FAQ
Comments (18)
THANK YOU, as always!!
ty too
Im a fan, just saying. 1,5 is NOT dead.
This model looks sick <3
This is by far one of my favorite checkpoints. It's very versatile, it can easily create everything from beautiful fantasy worlds to a zombie apocalypse.
Greetings from the land of the rising sun. /bow
Trying out this model for the first time and I really like it. Could you make an inpainting version of this, or is there an inpainting model you would recommend for using with it?
this model has a personality all of it's own - unique and superb work
Absolutely adore this checkpoint--one of my top 3.
Do you have a fp32 version of this model?
Why do you need the fp32 version when it is no different and even heavier
@DucHaiten isn't fp32 better for training lora or dreambooth?
@hourglassfcupslimwaist So you're talking about training, yes, but it makes the resource consumption double
you can convert it to fp32 if you want
This model is simply magical! I am absolutely delighted with this cool mysterious expressive cinematic look. The variability, flexibility, anatomical correctness and diversity are simply on top!
A wonderful model! Thanks!
I love your models so much ! One thing I've noticed is that it loves to bury my subjects into the ground, or put them in water. Any tips on the matter like neg or pos prompts, settings, et cetera? Also that it's difficult to get a full body in frame
How are yall getting realistic images I keep getting 3D
Check out the prompts of the example image of the blonde girl. Use photography, raw, uhd, eos, etc. etc. in positive prompt, use 3d, 2d, cgi etc. in negative prompt. I got some very realistic results while it is still very versatile and follows prompt
photorealistic, realistic, photography,
anime, cartoon, 2d, 3d, line drawing, and so forth in negative. You MIGHT need to remove anime from the negative to get some prompts to work. Usually this doesn't affect the realism at all but it can.