|
|
--- |
|
|
tags: |
|
|
- text-to-image |
|
|
- lora |
|
|
- diffusers |
|
|
- template:diffusion-lora |
|
|
widget: |
|
|
- output: |
|
|
url: images/out-2.webp |
|
|
text: A street scene in REALJLM |
|
|
- output: |
|
|
url: images/out-2.webp |
|
|
text: '-' |
|
|
base_model: black-forest-labs/FLUX.1-dev |
|
|
instance_prompt: REALJLM |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
# Jerusalem Images LORA |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## 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](/danielrosehill/Jerusalem-Images/tree/main) them in the Files & versions tab. |
