Instructions to use latent-consistency/lcm-sdxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use latent-consistency/lcm-sdxl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("latent-consistency/lcm-sdxl", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
controlnet SDXL lcm
#5
by henweber - opened
Great work!!
Im trying to make it work with ControlNet (depth) but images are not as good as using vanilla SDXL for example (I want to make them photorealistic but they come looking more like paintings).
Any idea why?
I’m going to produce some later today
This comment has been hidden
Sorry I wont be able to make such results any time soon, I had to move to another project. Thanks for the follow up.
henweber changed discussion status to closed