Instructions to use prompthero/openjourney with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prompthero/openjourney with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("prompthero/openjourney", 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
Question about mdjrny-v4.safetensors
#38
by pk11 - opened
I've seen the update today. As I'm using diffusers the model has been downloaded automatically. Thing is I have never installed the safetensors package. But I will do it now though. Thank you for taking care about our security.
The question is, what else beside installing safetensors should I do to enable the use of saftensors format of the model in the pipeline by default. Should I use it like with reviosion="safetensors" or will be there some kind of different setup required?
I get it now, the pipeline expects an sf_filename to be set. Should not it be done in one of the models JSON config-files?