🔴Patreon | Choose what i'll train next | PANyZHAL
━━━━━━━━━━━━ ◦ ❖ ◦ ━━━━━━━━━━━━
weight: 2. always. ALWAYS.
Hi! I know I only train this, but I like it so much! I hope you enjoy it too. This LoRA is supposed to work with models trained on SDXL because pony models aren't too good with backgrounds and SDXL LoRAs can't work on them. So, this model opens the possibilities to a new world.
Actually, the pony LoRA can also work with other SDXL models using the same trick that I am going to teach for this model.
The trick:
Put the
weight: 2. always. ALWAYS.
With this, in some generations, you almost don't need keywords, but to be sure, use them: disembodied head, headless, detached.
Recommendations:
WEIGHT: 2
For complex poses you can use depth maps
Description
Hi, I'm still working on this because I still haven't found the perfect way to make it work with character names, but I'm publishing it for you to test.
FAQ
Comments (8)
Quite often it creates the body with no head around. Any chance for a thrid lora that is just floating head, so I can inpain the heads back in?
Yes, perhaps that could be an alternative. I’ll search for a good dataset and maybe train it later.
@PANyZHAL appreciated!
@barlogspam176 Hello! Sorry for the delay. The model is ready now 😁 Only Head
@PANyZHAL amazing!
Does this only work with anime characters?
Hello! It also works with realism; just remember that it's most compatible with models based on PONY, although some users have managed to use it with other XL models.
Check some of my postings to see realistic ones done.