Auraflow DomoKun LoRA Rank8

🚀 Auraflow-DomoKun-LoRA-rank8

This project is a standard PEFT LoRA derived from fal/AuraFlow. It focuses on text - to - image and image - to - image tasks, offering a unique solution for generating relevant images.

🚀 Quick Start

Inference Example

import torch
from diffusers import DiffusionPipeline

model_id = 'fal/AuraFlow'
adapter_id = 'bghira/Auraflow-DomoKun-LoRA-rank8'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An domokun running through a field with flowers all around him."
negative_prompt = 'ugly, cropped, blurry, low-quality, mediocre average'

## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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
model_output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=30,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=512,
    height=512,
    guidance_scale=4.0,
).images[0]

model_output.save("output.png", format="PNG")

✨ Features

• Derived from fal/AuraFlow, it inherits the base model's capabilities.
• Supports text - to - image and image - to - image tasks.
• The text encoder was not trained, allowing reuse of the base model text encoder for inference.

📚 Documentation

Validation settings

• CFG: 4.0
• CFG Rescale: 0.0
• Steps: 30
• Sampler: FlowMatchEulerDiscreteScheduler
• Seed: 42
• Resolution: 512x512

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

You can find some example images in the following gallery: