Icon Generator

🚀 icon-generator

This project is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev, which is designed for generating minimalist icons.

🚀 Quick Start

This icon generator is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev. You can use it to generate various minimalist icons.

✨ Features

• Derived from black-forest-labs/FLUX.1-dev base model.
• Supports text-to-image generation for minimalist icons.
• Provides specific validation and training settings.

📦 Installation

The installation process mainly involves loading the base model and the adapter. You can use the following Python code to load the model and adapter:

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'noahyoungs/icon-generator'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

💻 Usage Examples

Basic Usage

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'noahyoungs/icon-generator'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "Minimalist icon, arrow up"

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
image = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")

Advanced Usage

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'noahyoungs/icon-generator'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "Minimalist icon, arrow up"

## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
image = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")

📚 Documentation

Validation settings

Note: The validation settings are not necessarily the same as the training settings.

Training settings

Datasets - tabler-icons-1024

🔧 Technical Details

The icon generator is based on the black-forest-labs/FLUX.1-dev base model and uses the PEFT LoRA technique. During training, specific settings such as learning rate, batch size, and LoRA parameters are configured. The text encoder of the base model is not trained, and it can be reused for inference.

📄 License

The license of this project is other.