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: CARAVAGGIO
widget:
  - text: Man having lunch in the style of CARAVAGGIO
    output:
      url: examples/5.webp
  - text: >-
      Man eating a donut sit on a chair, emphasize lights and shadows in the
      style of CARAVAGGIO
    output:
      url: examples/2.webp
  - text: A cup of coffe on a table in the style of CARAVAGGIO
    output:
      url: examples/3.jpeg
  - text: >-
      Medieval people dancing to music. Emphasize lights and shadows in the
      style of CARAVAGGIO
    output:
      url: examples/4.jpeg
  - text: >-
      A man petting a dog, emphasize lights and shadows in the style of
      CARAVAGGIO
    output:
      url: examples/1.webp
  - text: A man working on hid desk in the style of CARAVAGGIO
    output:
      url: examples/6.jpeg

Flux Lora Caravaggio

Prompt
Man having lunch in the style of CARAVAGGIO

Prompt
Man eating a donut sit on a chair, emphasize lights and shadows in the style of CARAVAGGIO

Prompt
A cup of coffe on a table in the style of CARAVAGGIO

Prompt
Medieval people dancing to music. Emphasize lights and shadows in the style of CARAVAGGIO

Prompt
Painting of a skull on a table, perspective at an angle. emphasize lights and shadows in the style of CARAVAGGIO

Prompt
A man working on his desk in the style of CARAVAGGIO

Trained on Replicate using:

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

Trigger words

You should use CARAVAGGIO 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('ludocomito/flux-lora-caravaggio', 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