Instructions to use artificialguybr/LogoRedmond-LogoLoraForSDXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use artificialguybr/LogoRedmond-LogoLoraForSDXL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("artificialguybr/LogoRedmond-LogoLoraForSDXL") prompt = "LogoRedAF" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Possible to speed up this model?
#2
by jonathanrstern - opened
Taking ~25 seconds to generate one image. Is there anything I can do to speed this up for a production application?
It depends entirely on your hardware. Lora doesn't change speed.