Instructions to use danielrosehill/Jerusalem-Images with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use danielrosehill/Jerusalem-Images with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("danielrosehill/Jerusalem-Images") prompt = "A street scene in REALJLM" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Jerusalem Images LORA

- Prompt
- A street scene in REALJLM

- Prompt
- -
Model description
A Flux LORA for generating realistic images of Jerusalem, Israel trained on a dataset of streetscape images taken around West Jerusalem during the summer of 2025 (images: Daniel Rosehill). Trainig was done using Replicate's Fast Flux Trainer.
My idea with the image dataset was to try to capture the part of the city I live in at both the "macro" and "micro" levels - hence the mixture of buildings and ... minutiae of daily life like manhole covers (!), electrical wiring, etc.
I also wanted to capture the contrast between the Old City of Jerusalem and the modern building going up all around town.
Trigger words
You should use REALJLM to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 4
Model tree for danielrosehill/Jerusalem-Images
Base model
black-forest-labs/FLUX.1-dev






