FLUX.1 Dev LoRA HuggingFaceIcons V0.1

🚀 FLUX.1-dev-LoRA-AutumnSpringTrees

This project is a LoRA fine - tune for FLUX.1 [dev], specializing in generating HuggingFace/SmolLM emoji icons. It can enhance FLUX.1 [dev]'s ability to generate Hugging Face Emoji Icons for new projects on Hugging Face.

Datasets

• Borcherding/HuggingFaceIcons - imageAnnotations - v0.1

Tags

• text - to - image
• lora
• diffusers
• template:diffusion - lora

Widget Examples

✨ Features

This LoRA enhances FLUX.1 [dev]'s ability to generate Hugging Face Emoji Icons for utility in new projects on hugging face. It allows you to create unique model cards for finetunes with a specific HF icon aesthetic.

📦 Installation

First, ensure you have FLUX.1 [dev] installed:

# Install
pip install -U diffusers

# Loading with Diffusers
import torch
from diffusers import FluxPipeline

# Load base model
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

# Load and apply LoRA weights
pipe.load_lora_weights("Borcherding/FLUX.1-dev-LoRA-HuggingFaceIcons-v0.1")

# Generate image
prompt = "HuggingFaceIcons a yellow smiley face sun with a book in its hands, surrounded by planets and stars in a dark background."
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=50,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("autumn-scene.png")

# Unload LoRA weights if needed
pipe.unload_lora_weights()

# Optional: Merge LoRA weights permanently
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Borcherding/FLUX.1-dev-LoRA-HuggingFaceIcons-v0.1")
pipe.merge_lora_weights()
pipe.save_pretrained("FLUX.1-dev-LoRA-HuggingFaceIcons-v0.1")

💻 Usage Examples

Basic Usage

To generate an image, use the following steps:

1. Install the necessary libraries as shown in the installation section.
2. Load the base model and apply the LoRA weights.
3. Use a prompt with the trigger word HuggingFaceIcons.

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()
pipe.load_lora_weights("Borcherding/FLUX.1-dev-LoRA-HuggingFaceIcons-v0.1")

prompt = "HuggingFaceIcons a yellow smiley face sun with a book in its hands, surrounded by planets and stars in a dark background."
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=50,
    max_sequence_length=512,
    generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("example.png")

🔧 Technical Details

• Base Model: black - forest - labs/FLUX.1 - dev
• Instance Prompt: autumnProxy
• License: apache - 2.0

📄 License

This LoRA falls under the same licensing terms as FLUX.1 [dev]. Please refer to the base model's license for usage terms.

Credits

• Base model: FLUX.1 [dev] by Black Forest Labs
• LoRA training and development: [Borcherding at BorchInk]

Trigger words

You should use HuggingFaceIcons to trigger the image generation. Best results are achieved when placing the trigger word at the start of the prompt.

Download model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

Limitations

• This is a LoRA for FLUX.1 [dev] and requires the base model to function.
• It focuses on Hugging Face Icons.
• It is trained on a small dataset.
• It inherits base limitations from FLUX.1 [dev].