Instructions to use realrebelai/RebelMidjourney_Z-Image_LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use realrebelai/RebelMidjourney_Z-Image_LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("realrebelai/RebelMidjourney_Z-Image_LoRA") prompt = "-" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
RebelMidjourney (Z-Image LoRA)
Midjourney LoRA for Z-Image-Turbo!
RECOMMENDED STRENGTH:
0.2 - 0.8
adds the midjourney aesthetic to your generations. VERY well trained to be as close to Midjourney as possible.
Dataset: 1217 Images
Learning Rate: 0.00005
Training Step Total: 2000 steps (3k was too much and overcooked the lora so i stuck with 2k as a good medium.)
WARNING: LORA IS STRONG. i recommend testing on 0.1 and working your way up to the desired strength per image.

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -
Download model
Download them in the Files & versions tab.
- Downloads last month
- 62
Model tree for realrebelai/RebelMidjourney_Z-Image_LoRA
Base model
Tongyi-MAI/Z-Image-Turbo