Instructions to use bdsqlsz/qinglong_controlnet-lllite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use bdsqlsz/qinglong_controlnet-lllite with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("bdsqlsz/qinglong_controlnet-lllite", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Tile Training Details
#6
by kitsuneautodraft - opened
Hey,
I wanted to gain some insight as to how the data preparation for the tile model was done? What kind of preprocessing was done and the corresponding original and tile images, it would be really insightful to know.
Thanks!
preprocesser with controlnet tile
datasets reference in below
https://github.com/kohya-ss/sd-scripts/blob/sdxl/docs/train_lllite_README.md