metadata
license: apache-2.0
Aesthetic Enhancement - Kontext Image Editing LoRA
Model Introduction
This LoRA model is trained based on the Kontext model and DiffSynth-Studio. After using this model, you can input the instruction Enhance the aesthetic quality of this image. to enhance the aesthetic quality of an image. The model automatically analyzes aspects such as lighting and composition based on the image content and adjusts them to make the image more visually appealing. This model can be applied repeatedly, meaning you can perform aesthetic enhancement multiple times on an already enhanced image.
Model Results
| Example 1 | Example 2 | Example 3 | |
|---|---|---|---|
| Original |  |
 |
 |
| 1st Enhancement |  |
 |
 |
| 2nd Enhancement |  |
 |
 |
| 3rd Enhancement |  |
 |
 |
| Example 4 | Example 5 | Example 6 | |
|---|---|---|---|
| Original |  |
 |
 |
| 1st Enhancement |  |
 |
 |
| 2nd Enhancement |  |
 |
 |
| 3rd Enhancement |  |
 |
 |
Usage Instructions
This model is built on the DiffSynth-Studio framework. Please install it first:
git clone https://github.com/modelscope/DiffSynth-Studio.git
cd DiffSynth-Studio
pip install -e .
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
from PIL import Image
from modelscope import snapshot_download
snapshot_download("DiffSynth-Studio/FLUX.1-Kontext-dev-lora-ArtAug", cache_dir="./models")
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
],
)
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/FLUX.1-Kontext-dev-lora-ArtAug/model.safetensors", alpha=1)
image = Image.open("your_image.jpg")
image = pipe(
prompt="Enhance the aesthetic quality of this image.",
kontext_images=image,
embedded_guidance=2.5,
seed=0,
)
image.save("output.jpg")