metadata

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: '2004'
widget:
  - text: a bad 2004 photo, harsh flash
    output:
      url: images/example_calk81u89.png
  - text: a bad 2004 photo of a living room interior, harsh flash
    output:
      url: images/example_t9zz1xby3.png
  - text: a bad 2004 photo of a car, harsh flash
    output:
      url: images/example_tdyzalbwe.png

Flux 2004

Prompt
a bad 2004 photo of a living room interior, harsh flash

Prompt
a bad 2004 photo of a car, harsh flash

Run on Replicate:

https://replicate.com/fofr/flux-2004

Trained on Replicate using:

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

Trigger words

You should use 2004 to trigger the image generation.

Use it with the 🧨 diffusers library

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('fofr/flux-2004', 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