flux-latentpop Open-source Illustration Generation Model - Free Generation of Silk Screen Printing-style T-shirt Designs and Character Portrait Illustrations

Flux Latentpop

Developed by jakedahn

Flux latentpop is a LoRA model based on FLUX.1-dev, specializing in generating illustrations with a screen printing style and limited colors, particularly suitable for T-shirt designs and character portraits.

Image Generation EnglishOpen Source License:Other #Screen printing style #T-shirt design #Cartoon illustration

Downloads 86

Release Time : 8/25/2024

Model Overview

This model features vibrant backgrounds and bold, limited screen printing color effects, making it ideal for T-shirt designs, general illustrations, and character portrait creation.

Model Features

Screen printing style

Generates images with bold, limited color effects that mimic the artistic style of screen printing.

High adaptability

Suitable for various illustration scenarios, including T-shirt designs, character portraits, and general illustrations.

Specific trigger word

Use 'LNTP' as the trigger word to achieve the best stylistic results.

Model Capabilities

Text-to-image generation

Stylized illustration generation

T-shirt design generation

Use Cases

Fashion design

T-shirt pattern design

Generate screen printing-style patterns suitable for printing on T-shirts.

Examples include a happy cat pattern with the slogan 'I LOVE VE REPLICATE'.

Illustration creation

Character portraits

Generate character portraits with specific artistic styles.

Examples include a little girl playing piano and a robot character.

🚀 Flux latentpop

Flux-latentpop offers vibrant backgrounds combined with the charm of grungy limited screenprinting colors. It excels in creating t-shirt designs, general illustrations, and character portraits.

🚀 Quick Start

Flux-latentpop features vibrant backgrounds with grungy limited screenprinting color goodness. It does great with t-shirt designs, general illustrations, and character portraits.

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 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

✨ Features

Offers vibrant backgrounds with grungy limited screenprinting color goodness.
Performs well in t-shirt designs, general illustrations, and character portraits.

💻 Usage Examples

Basic Usage

You should use LNTP to trigger the image generation. The output images look more stylistically interesting with a guidance_scale of ~2.5.

Advanced Usage

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

📄 License

License Name: flux-1-dev-non-commercial-license
License Link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

Property	Details
Model Type	Flux latentpop
Training Data	23 images generated on MidJourney using the `--sref 3102110963` and `--personalize 3xdy3qw` flags. Entire training set can be found in `./2024-08-24-latentpop.zip`

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご