veryBadImageNegative - veryBadImageNegative_v13
é¢é£ããŒã¯ãŒãïŒã¿ã°
ãã€ã©ã€ããããç»å
æšå¥šããã³ãã
(((masterpiece,best quality,official art,extremely detailed CG unity 8k wallpaper))),illustration,landscape,solo,1girl,bishojo,beautiful detailed eyes,Student uniforms
æšå¥šãã¬ãã£ãããã³ãã
no prompt
æšå¥šãã©ã¡ãŒã¿
samplers
steps
cfg
resolution
other models
æšå¥šãã€ã¬ãŸãã©ã¡ãŒã¿
upscaler
upscale
steps
denoising strength
ãã³ã
veryBadImageNegative_v1.2ã䜿çšããéãæè»æ§ãé«ããããã«ãŠã§ã€ããæžããããšãã§ããŸããäŸ: (veryBadImageNegative_v1.2-6400:0.9)
ãã¬ãŒãã³ã°ã¹ãããã®æ°(1600 ~ 6400)ã¯ãã¬ãŒãã³ã°äžã®ã¹ãããæ°ã衚ããŠããŸããçè«çã«ã¯ã¹ããããå€ããã°å€ãã»ã©å¹æãè¯ããªããŸãã
v1.3
veryBadImageNegative_v1.3ã¯æ°ãããã¬ãŒãã³ã°ã¢ãã©ã¹ã䜿çšããAOM3ãviewer-mix_v1.7ã§åªããæ§èœãçºæ®ããŸãã
veryBadImageNegative_v1.3 uses a new training atlas and performs well when used in AOM3 and viewer-mix_v1.7.
v1.2
veryBadImageNegativeã¯viewer-mix_v1.3ã§çæãããç¹å¥ãªã¢ãã©ã¹ã䜿çšããŠãã¬ãŒãã³ã°ããããã¬ãã£ããšã³ããã£ã³ã°ã§ãã
ãããã£ãŠãveryBadImageNegativeã¯viewer-mix_v1.3ã®å°çšãã¬ãã£ããšã³ããã£ã³ã°ã§ãã
ä»ã®æ¡æ£ã¢ãã«ã§ãè¯å¥œãªå¹æããããããããŸããããæ€èšŒãäžè¶³ããŠããŸãã
veryBadImageNegative is a negative embedding trained from the special atlas generated by viewer-mix_v1.3.
So veryBadImageNegative is the dedicated negative embedding of viewer-mix_v1.3.
It may also have a good effect in other diffusion models, but it lacks verification.
v1.2ã«ã€ããŠïŒ
ç»åã®è³ªãé«ããã¹ã¿ã€ã«ã匱ããŸãã
v1.2ã䜿çšããéããŠã§ã€ããæžããããšã§æŽã«è¯ãæè»æ§ãåŸãããšãã§ããŸãã
äŸ: (veryBadImageNegative_v1.2-6400:0.9)
About v1.2:
Enhance image quality and weaken style.
When using v1.2, you can reduce some weights to obtain better flexibility.
For example: (veryBadImageNegative_v1.2-6400:0.9)
v1.0ãšv1.1ã®éãã«ã€ããŠïŒ
ã»ãšãã©éãã¯ãããŸããããã¬ãŒãã³ã°ã«äœ¿çšãããã¢ãã©ã¹ã¯çæãã©ã¡ãŒã¿ã«è¥å¹²ã®éãããããŸãã
1600~6400ã®å·®ç°ã«ã€ããŠïŒ
æ°åã¯ãã¬ãŒãã³ã°ã¹ãããæ°ã衚ããçè«çã«ã¯ã¹ãããæ°ãå€ããã°å¹æãè¯ããªããŸãã
About the difference between v1.0 and v1.1:
There is almost no difference. The atlas used for training only has some subtle differences in the generation parameters.
About the difference between 1600 ~ 6400:
The number represents the number of training steps. In theory, the more steps, the better the effect.
ã¢ãã«è©³çް
ã¢ãã«ã¿ã€ã
ããŒã¹ã¢ãã«
ã¢ãã«ããŒãžã§ã³
ã¢ãã«ããã·ã¥
åŠç¿æžã¿ã¯ãŒã
äœæè
ãã£ã¹ã«ãã·ã§ã³
ã³ã¡ã³ããæ®ãã«ã¯ log in ããŠãã ããã