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: https://huggingface.co/jakedahn/flux-latentpop/resolve/main/2024-08-24-latentpop.zip?download=true
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,
"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
描述:
训练词语: LNTP
名称: lora.safetensors
大小 (KB): 251843
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
