merve's picture
merve HF staff
Create README.md
8b990df verified
---
license: other
library_name: diffusers
tags:
- text-to-image
- diffusers-training
- diffusers
- lora
- flux
- flux-diffusers
- template:sd-lora
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: lego set in style of TOK
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# Flux DreamBooth LoRA - merve/flux-lego-lora-dreambooth
<Gallery />
## Model description
These are merve/flux-lego-lora-dreambooth DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev.
The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [Flux diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md).
Was LoRA for the text encoder enabled? False.
## Trigger words
You should use `lego set in style of TOK` to trigger the image generation.
## Download model
[Download the *.safetensors LoRA](https://huggingface.co/merve/flux-lego-lora-dreambooth/blob/main/pytorch_lora_weights.safetensors) in the Files & versions tab.
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('merve/flux-lego-lora-dreambooth', weight_name='pytorch_lora_weights.safetensors')
image = pipeline('lego set in style of TOK, a horse eating a ramen').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## License
Please adhere to the licensing terms as described [here](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).