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: >-
screenprint tshirt design, a happy cat holding a sign that says "I LOVE
VE REPLICATE", LNTP illustration style
output:
url: images/1.webp
- text: a t-shirt, LNTP illustration style
output:
url: images/2.webp
- text: a young girl playing piano, yellow background, LNTP illustration style
output:
url: images/3.webp
- text: >-
a book with the words 'Don't Panic!' written on cover, an homage to the
hitchhikers guide to the galaxy, LNTP cartoon style
output:
url: images/4.webp
- text: a robot, blue background, LNTP illustration style
output:
url: images/5.webp
- text: girl, orange background, LNTP illustration style
output:
url: images/6.webp
instance_prompt: LNTP
Flux latentpop
flux-latentpop features vibrant backgrounds with grungy limited screenprinting color goodness.
It does great with t-shirt designs, general illustrations, and character portraits.
- Prompt
- screenprint tshirt design, a happy cat holding a sign that says "I LOVE VE REPLICATE", LNTP illustration style
- Prompt
- a t-shirt, LNTP illustration style
- Prompt
- a young girl playing piano, yellow background, LNTP illustration style
- Prompt
- a book with the words 'Don't Panic!' written on cover, an homage to the hitchhikers guide to the galaxy, LNTP cartoon style
- Prompt
- a robot, blue background, LNTP illustration style
- Prompt
- girl, orange background, LNTP illustration style
It was trained on Replicate, here: https://replicate.com/ostris/flux-dev-lora-trainer/train
The training set is comprised of 23 images generated on MidJourney using the --sref 3102110963 and --personalize 3xdy3qw flags. You can find the entire training set here in this repo: ./2024-08-24-latentpop.zip
Below are the training parameters I used, which seem to work fairly well for illustration/cartoony Flux LoRAs:
{
"steps": 1300,
"lora_rank": 24,
"optimizer": "adamw8bit",
"batch_size": 4,
"resolution": "512,768,1024",
"autocaption": true,
"input_images": "https://replicate.delivery/pbxt/Lg3C1KUPfrRZZvJFaaSTmQ9qtAyXSonLvLSuTuj4Nop9vcSu/2024-08-24-latentpop.zip",
"trigger_word": "LNTP",
"learning_rate": 0.0002,
"autocaption_suffix": "LNTP style",
"caption_dropout_rate": 0.05,
}
Shoutout to @ciguleva on x who originally shared this sref on x: https://x.com/ciguleva/status/1827398343779098720
Usage
You should use LNTP to trigger the image generation. The output images look more stylistically interesting with a guidance_scale of ~`2.5`.
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-latentpop', 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