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: CONDENSATION
widget:
  - text: the word "hello" written in CONDENSATION on the window
    output:
      url: images/example_2d3sjnkvb.png
  - text: the word "You suck!" written in CONDENSATION on the window
    output:
      url: images/example_crzf2b8xi.png
  - text: the word "Hugging Face" written in CONDENSATION on the window
    output:
      url: images/example_loupqxabk.png

Flux Condensation

Prompt
the word "hello" written in CONDENSATION on the window

Prompt
the word "You suck!" written in CONDENSATION on the window

Prompt
the word "Hugging Face" written in CONDENSATION on the window

Trained on Replicate using:

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

Trigger words

You should use CONDENSATION 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-condensation', 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