license: apache-2.0
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
- pen
- calligraphy
- typography
- lettering
- medieval type
- tattoo font
- graphic design
- font
- vintage
- retro
- art direction
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: TOK
Retro Pen Lettering Flux Lora
Sharing here the first of my Flux LoRas for Graphic Designers, Art directors and Creative Industries. A fine tuned retro pen lettering and calligraphy model for Flux-dev.
Dataset from old lettering books, carefully selected, upscaled, refined and manual captioned for better quality and adherence.
I share here some unrefined and uncherry-picked outputs, along with a sample photo of the dataset used for this special LoRa for typography lovers. Share your generations! 🧙♂️🌟
⬇Download from Civitai⬇ https://civitai.com/models/655773?modelVersionId=733682
⬇You can test it using this workflow for free on OpenArt AI⬇ https://civitai.com/models/655773/retro-pen-lettering (outdate but working fine)
Triggers: TOK, in the style of TOK
Best setup is:
CFG: 3-4
Euler - Normal
Steps: 25-30
Outputs
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('Agusdor/pen_lettering_flux_lora', 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