README.md

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
widget:
  - text: >-
      funny cat holding a sign "I <3 REPLICATE", dark blue scene, illustrated
      MSMRB style
    output:
      url: images/1.webp
  - text: >-
      a cat licking a large felt ball with a drawing of the Golden Gate Bridge
      on it, illustrated MSMRB style
    output:
      url: images/2.webp
  - text: >-
      funny white cat holding a sign "I <3 REPLICATE", sketch, grainy storybook
      illustration, black and white, illustrated MSMRB style
    output:
      url: images/3.webp
  - text: cat with a hat, illustrated MSMRB style
    output:
      url: images/4.jpg
  - text: man wearing a suit, illustrated MSMRB style
    output:
      url: images/5.jpg
  - text: san francisco, illustrated MSMRB style
    output:
      url: images/6.webp
instance_prompt: MSMRB

Flux Midsummer Blues

Prompt

funny cat holding a sign "I <3 REPLICATE", dark blue scene, illustrated MSMRB style

Prompt

a cat licking a large felt ball with a drawing of the Golden Gate Bridge on it, illustrated MSMRB style

Prompt

funny white cat holding a sign "I <3 REPLICATE", sketch, grainy storybook illustration, black and white, illustrated MSMRB style

Prompt

cat with a hat, illustrated MSMRB style

Prompt

man wearing a suit, illustrated MSMRB style

Prompt

san francisco, illustrated MSMRB style

Trained on Replicate using:

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

Trigger words

You should use MSMRB 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('jakedahn/flux-midsummer-blues', 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