Demo images use Danger Zoo ~ Johnsons Negative TI Collection ~
"modelname style" is the main trigger word
additional trigger words are listed to keep you close to the trained style/concepts.
This LORA is designed for used with other djz LORA's and/or on top of Mixed pairs of djz CKPT's or a Triple merge mix including other CKPT models. This is a specific method for merged CKPT models while running a stack of these Style LORA models on top. You may still use this alone and it is recommended to include the additional trigger words in your prompts.
DJZ Season 2.5
Description
FAQ
Comments (3)
Hi, I'm getting
"RuntimeError: The size of tensor a (768) must match the size of tensor b (1024) at non-singleton dimension 1"
with all your recent loras, tried with different checkpoints 1.5 and 2.1, everywhere getting this error.
ok, this does not work with 1.5 or 2.1, these are typically 512x base models.
If you use 2.1-768 models these Lora's will work. If they still fail something is wrong with your webUI
with automatic i use this:
set COMMANDLINE_ARGS= --medvram --xformers --opt-split-attention
In my startup args. I'm using Automatic WebUI updated on March 23rd.
I will download the LORA and create some images, then post them to check the files, but i get this comment a lot. The error is telling you that you didn't run a 768x model. Good luck!
(consider testing with axsUltraLumin, which i use for testing 2.1-768 Lora's)
@driftjohnson thanks! Worked with axsUltraLumin and Illuminutty Diffusion. Now I know that there are different 2.1 models =)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.