Instructions to use alimama-creative/slam-lora-sdxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use alimama-creative/slam-lora-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("alimama-creative/slam-lora-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
Use on distilled models?
#1
by Aptronym - opened
Giving this a try as I think it will be extremely useful for a project I'm working on, but I'm wondering if it's possible to apply this to distilled SDXL models. Models such as Koala 700/1b, segmind vega, etc.
There is an existing Koala 700 and 1b Lightning version now, and I'll check with them on how they accomplished that too, but wondering if you had any thoughts or ideas? Being able to apply this to more than just base sdxl models would give people better looking options that were also fast.