Introduction (V2 out)
Tim Burton is an American filmmaker and animator. He is known for his gothic fantasy and horror films like Edward Scissorhands, Sleepy Hollow and Beetlejuice.
Burtonesque is not a very well defined style but caricature like & gothic features are very prominent. I enjoyed creating this model because the style is very unique. I couldn't reproduce it in base models without LoRA.
The LoRA is great at making portraits. I recommend using it between 0.7-0.9 strength with AnythingV3. You should also use simple prompts and negative prompts to preserve the style.
I have idiopathic hypersomnia and I need coffee to stay awake. Buy me a coffee? 0xf5c985d0EAb52B34C6F5c214BdC684E315CbDd18 (Any chain)
Description
More coherent (better colors, gamma, contrast and details).
Generally better results.
A bit more flexible.
Better at danbooru style prompting.
FAQ
Comments (4)
hello, i have a problem with V2 it gives me this error burtonesque2.safetensors: RuntimeError | 0/31 [00:00<?, ?it/s]
Traceback (most recent call last):
File "E:\ai\AI\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 215, in load_loras
lora = load_lora(name, lora_on_disk.filename)
File "E:\ai\AI\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 176, in load_lora
module.weight.copy_(weight)
RuntimeError: output with shape [32, 320, 1, 1] doesn't match the broadcast shape [32, 320, 3, 3]
But only with v2, when i use v1 it works without a problem. Any ideas?
Unfortunately v1.5 LoRAs won't work for SD version 2 and above. That's the case for all LoRAs. Try vanilla SD 1.5 or another model, it should work.
@MR_BEEP I do not use SD 2. by V2 i meant Burtonesque Style (v2 out!) the v1 version works without problem :/
@MR_BEEP Solved. I had to install locon extension :O
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.