import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("calcuis/illustrious", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Ava2000/Branch_BlackRabbits_Illustrious")
prompt = "masterpiece, best quality, traditional media, jaggy lines, sketch,"
image = pipe(prompt).images[0]Branch (Blackrabbit) style - Illustrious
- Prompt
- masterpiece, best quality, traditional media, jaggy lines, sketch,
- Negative Prompt
- text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor, cameltoe,
Model description
The style of Branch.
My version of the Branch (Blackrabbits) Style trained on Pony Diffusion and Illustrious.
Illustrious V2
I remade this lora because I'm more experienced and mistakes were made with version one.
First off, for the quality tags I use the following: masterpiece, best quality, traditional media, jaggy lines, sketch, (to make it match the original art style better).
For the negatives I use the following: text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor, (showcase images has also cameltoe, but I forgot to remove that one)
I didn't use ADetailer for this one, but can be used to up the quality.
The Trigger is: blackrabbit,
Advised strength: 0.6-1.0
Trigger words
You should use blackrabbit to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 23
Model tree for Ava2000/Branch_BlackRabbits_Illustrious
Base model
KBlueLeaf/kohaku-xl-beta5