DucHaiten-AIart-SDXL
Creator: DucHaiten
Added Lightning version of v3.3.5.1.5, in just 13 steps you can create stunning high-quality photos, but please note the following important parameters:
Some notes when using the Lightning model:
Sampling method: Euler a (You can try other sampling methods, but most of them are unusable)
Sampling steps: 13 (If it is lower, it will lack important details, but if it is higher, redundant details will appear)
CFG Scale: 1,5 (Lower will not have enough accuracy or sharpness or vivid colors in the image, and anything higher will cause spots and color errors to appear)
Negative prompt: (This doesn't have to be the same as mine, perhaps yours might be even better.)
(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, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist.
Some people have reported bugs in the v3 version, so this v3.3.5.1.5 will be a bug fix version for v3.
The v3 version has a lot of improvements that touch the original data, it's a big fine-tuning, so I know there will be some people who will feel uncomfortable and not like this new version, but I decided to do it. so that the model can be more harmonious, generalize better, and also become more diverse. The old v2 version was highly rated, but it had a lot of problems that needed to be fixed like the lighting was too artificial, everything was too bright, the shadows were not accurate, the faces were too stereotypical, the drawings were too comics, thick and rough. All of that makes v2 exceptionally good at certain prompts, but exceptionally bad at most others. So in this v3 version I've changed it a lot, maybe with some prompts you got extremely good results in v2 which are no the same as before, but it will be averagely good in all the diverse prompt types. but if you still prefer v2 then v2 is still there, that's your choice
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, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist
Steps: 50
Sampler: Euler a
CFG scale: 9
Size: 1024
DucHaiten-AIart-SDXL
Creator: DucHaiten
Added Lightning version of v3.3.5.1.5, in just 13 steps you can create stunning high-quality photos, but please note the following important parameters:
Some notes when using the Lightning model:
Sampling method: Euler a (You can try other sampling methods, but most of them are unusable)
Sampling steps: 13 (If it is lower, it will lack important details, but if it is higher, redundant details will appear)
CFG Scale: 1,5 (Lower will not have enough accuracy or sharpness or vivid colors in the image, and anything higher will cause spots and color errors to appear)
Negative prompt: (This doesn't have to be the same as mine, perhaps yours might be even better.)
(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, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist.
Some people have reported bugs in the v3 version, so this v3.3.5.1.5 will be a bug fix version for v3.
The v3 version has a lot of improvements that touch the original data, it's a big fine-tuning, so I know there will be some people who will feel uncomfortable and not like this new version, but I decided to do it. so that the model can be more harmonious, generalize better, and also become more diverse. The old v2 version was highly rated, but it had a lot of problems that needed to be fixed like the lighting was too artificial, everything was too bright, the shadows were not accurate, the faces were too stereotypical, the drawings were too comics, thick and rough. All of that makes v2 exceptionally good at certain prompts, but exceptionally bad at most others. So in this v3 version I've changed it a lot, maybe with some prompts you got extremely good results in v2 which are no the same as before, but it will be averagely good in all the diverse prompt types. but if you still prefer v2 then v2 is still there, that's your choice
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, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist
Steps: 50
Sampler: Euler a
CFG scale: 9
Size: 1024
