README.md

---
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
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
instance_prompt: CNSTLL
widget:
  - text: in the style of CNSTLL, a white car parked in front of a gas 
          station, night time, cinestill 800T
    output:
      url: 1.png
  - text: >-
      in the style of CNSTLL , urban landscape, people fishing on Galata 
      bridge in Istanbul at night
    output:
      url: 2.png
  - text: >-
      in the style of CNSTLL , photo of New York City at night, 4k
    output:
      url: 3.png
  - text: >-
      in the style of CNSTLL, an urban landscape with street sellers and 
      a fish market at night, photorealistic
    output:
      url: 4.png
---

# Flux Cinestill
<Gallery />

FLUX.1-Dev LoRA fine tuned on Cinestill 800T images on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train

Best suited for generating night and dusk time photograph-like images with a distinctive slight halation effect. Keywords that result in better generations "cinestill 800t", "night time", "dusk", "4k", "high resolution", "analog film".

## Trigger words
You should use `CNSTLL` to trigger the image generation.


## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('adirik/flux-cinestill', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)