Edit model card

Flux.1-Dev LoRA Adapter Trained on ABAII Logo

LoRA Adapter for black-forest-labs/FLUX.1-dev trained on 22 pictures of ABAII Logo with ai-toolkit

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

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 for all details on appropriate usage, licensing, and more.

Downloads last month
12
Inference API
Examples

Model tree for dtthanh/abaii_logo

Adapter
(9253)
this model