This absolutely blursed LORA is brought you to in concept and post by me, while having been beautifully trained and supplied to me by a fellow ProjectAI server member, Sikinix.
Two versions, both work with pretty much anything. Refer to the listed trigger words and you'll be laughing your ass off in no time.
Somehow there is a way to trigger just the eyes and no mouth, but I'm unsure of how that is achieved.
Images in preview may be from past versions! Do not expect full replication!
MAKE SURE YOU HAVE LOCON INSTALLED👁️👁️
Description
Presumably less stronger than cooked, trigger words remain the same. Previews here are credited to Sikinx
FAQ
Comments (11)
This happens when I try to use it
activating extra network lora with arguments [<modules.extra_networks.ExtraNetworkParams object at 0x000002B13961C700>]: AssertionError\nTraceback (most recent call last): File "<path>\modules\extra_networks.py", line 75, in activate extra_network.activate(p, extra_network_args) File "<path>\extensions-builtin\Lora\extra_networks_lora.py", line 23, in activate lora.load_loras(names, multipliers) File "<path>\extensions-builtin\Lora\lora.py", line 213, in load_loras lora = load_lora(name, lora_on_disk.filename) File "<path>\extensions-builtin\Lora\lora.py", line 184, in load_lora assert False, f'Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha' AssertionError: Bad Lora layer name: lora_unet_down_blocks_0_downsamplers_0_conv.lora_mid.weight - must end in lora_up.weight, lora_down.weight or alphahmmm. maybe make sure you have locon installed?
yeah that looks like the issue. (found this while trying to fix it https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/8360#issuecomment-1456933843 )
BRO WHAT AM I SEEING 😭😭😭😭🤣🤣🤣🤣
brother what the hell
The Lora we never asked for because we never knew we needed it, only not reviewing because I haven't tested it but consider this comment 5 stars.
This is great, how do you even train concepts like this?
Well, since I created the dataset, what I had to do was take the actual time to basically photoshop the face onto every piece of art in the dataset. It wasnt as tedious, as long as i had something to listen to as a i did it.
@Annawn Dedication 100, I respect it!
wait...what?
This... is horrifying.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.