license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: analog photo in the style of EXPRDFLMEFCT
widget:
- text: >-
analog photo in the style of EXPRDFLMEFCT, a young woman sitting on a
subway train. She is wearing a brown jacket and blue jeans. She has blonde
hair and is looking down at her phone. There is a black bag on her lap
next to her. The train has orange seats and there is a window on the right
side of the image. The background is blurred, but it appears to be a
subway station, film grain, film noise
output:
url: camera1/1.jpg
- text: >-
analog photo in the style of EXPRDFLMEFCT, a woman wearing a yellow
sundress, holding flowers and holding her straw hat from flying due to
winds, hair swaying, standing in front of an ocean, ship in the
background, guard rails, sunny afternoon, film grain, film noise
output:
url: camera1/2.jpg
- text: >-
analog photo in the style of EXPRDFLMEFCT, a woman wearing glasses, a
baseball cap and a scarf, standing in front of old dilapidated lighthouse,
crashing waves, dimly lit, film grain, film noise
output:
url: camera1/3.jpg
- text: a woman, smiling
output:
url: camera2/1.jpg
- text: >-
analog photo in the style of EXPRDFLMEFCT, a boy, reading a book. sitting
on a bench in a park, film grain, film noise
output:
url: camera2/2.jpg
- text: >-
analog photo in the style of EXPRDFLMEFCT, a cat, sleeping in a field of
lavender flowers, film grain, film noise
output:
url: camera2/3.jpg
flux-film-camera
Model description
Flux LoRAs for creating an analog photo effect. Use 'analog photo in the style of EXPRDFLMEFCT' to trigger both models. Best with DEV (works well even with fp8). To use with flux1-dev-bnb-nf4 try increasing the LoRA strength (to say 1.3 and then adjust accordingly).
CAMERA-1.safetensors (Soft): produces a bit soft and tinted images
CAMERA-2.safetensors (HDR): produces images with better dynamic range
Try both models easily at https://glif.app/@bingbangboomlab/glifs/cm2h7dj8a000060xh5i2ps5fh
Trigger words
You should use analog photo in the style of EXPRDFLMEFCT
to trigger the image generation. you can also use append keywords like "film grain" and "film noise" in your prompt.
Download model
Weights for both models are available in Safetensors format.
Download them in the Files & versions tab.