SectorSaveBox

About this LoRA

This is a LoRA for the FLUX.1-dev text-to-image model. It can be used with diffusers, ComfyUI, or Replicate.

It was trained on Replicate using AI toolkit: ostris/flux-dev-lora-trainer

Trigger words

You should use sectorSaveBox to trigger the image generation.

Prompting Tips

You can combine it with environments, lighting styles, or action verbs. Examples:

• sectorSaveBox, on a white wall, close-up product photo
• sectorSaveBox, a person holding the device indoors
• sectorSaveBox, studio-lit product showcase

Run this LoRA with an API using Replicate

import replicate

input = {
    "prompt": "sectorSaveBox",
    "lora_weights": "https://huggingface.co/KAPPA66/sectorSaveBox/resolve/main/lora.safetensors"
}

output = replicate.run(
    "black-forest-labs/flux-dev-lora",
    input=input
)
for index, item in enumerate(output):
    with open(f"output_{index}.webp", "wb") as file:
        file.write(item.read())

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('KAPPA66/sectorSaveBox', weight_name='lora.safetensors')
image = pipeline('sectorSaveBox').images[0]

## Training details

- Steps: 1000  
- Learning rate: 0.0004  
- LoRA rank: 16  

## Contribute your own examples

Use the [community tab](https://huggingface.co/KAPPA66/sectorSaveBox/discussions) to share images you've made with this LoRA.