Instructions to use prompthero/openjourney-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prompthero/openjourney-v4 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-v4", 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
Do you plan to share your dataset of MJ image & text pairs?
#5
by ProGamerGov - opened
It would help improve the community's ability to replicate Midjourney.
It would help improve the community's ability to replicate Midjourney.
replicate MJ? or the variant of Openjourney? Coz i dont think the guys at Midjourney would like that, heck they started crying on the name before let alone "replicate" what they have. -.-
This comment has been hidden
Well, the model "doesn't use the images it's been trained on" it only gets a feel for how to render the things afaik, so I think you can just scrape MJ's discord/FB/insta and train your model on them.