---
tags:
- text-to-image
- lora
- diffusers
- flux
base_model: black-forest-labs/FLUX.1-dev
license: creativeml-openrail-m
library_name: diffusers
---
# Flux.1-Dev LoRA Adapter Trained on ABAII Logo
LoRA Adapter for [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) trained on 22 pictures of ABAII Logo with [ai-toolkit](https://github.com/ostris/ai-toolkit/tree/main)
# Model Details
**Some Examples**
LoRA was trained with the trigger phrase `with the ABAII logo. The logo features a stylized arrow design in shades of green and blue, with a pixelated effect on the green side. Below the logo, the text reads "ABAII" in bold black letters, followed by "Academy of Blockchain and AI Innovation" in smaller font.`
# Usage
With diffusers package
*Note: FLUX uses ~70GBvram when loaded directly with diffusers*
*Note: Recommended to load at ~70% scale for best results*
```python
from diffusers import DiffusionPipeline
pipeline = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev")
pipeline.load_lora_weights("dtthanh/abaii_v1", weight_name="abaii_v1.safetensors")
pipeline.to("cuda")
prompt = "A photo of a lady wearing a suit and inside a T-shirt with the small ABAII logo at her chest. The small logo features a stylized arrow design in shades of green and blue, with a pixelated effect on the green side. Below the logo, the text reads "ABAII" in bold black letters. The person is sitting at a wooden table, working on a laptop, with books and a notebook nearby. The background includes a bookshelf filled with CDs and a decorative wall."
out = pipeline(
prompt=prompt,
guidance_scale=3.5,
num_inference_steps=20,
cross_attention_kwargs={"scale": 0.7}
).images[0]
out.save("abaiilogo.png")
```
# Additional Details
Please see base model page [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) for all details on appropriate usage, licensing, and more.