Instructions to use DirtScan/trail-delighter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DirtScan/trail-delighter with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-4B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("DirtScan/trail-delighter") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Trail Delighter โ FLUX.2 Klein 4B LoRA
This is a LoRA for FLUX.2 Klein 4B specifically for the task of giving natural light to mountain bike trail photographs.
The process was as follows:
- Photos are taken of a mountain bike trail (often sunny, cast shadows, lens flare, glare)
- A selection of these were de-lighted using https://fal.ai/models/fal-ai/qwen-image-edit-2509-lora-gallery/lighting-restoration - This creates a "teacher set"
- This teacher set was then used to train a new LoRA, but with a base of FLUX.2 Klein 4B (instead of Qwen) - overall making the model smaller and easier to run.
License
The adapter is provided under Apache-2.0, subject to the terms of the base FLUX.2 Klein model.
- Downloads last month
- -
Model tree for DirtScan/trail-delighter
Base model
black-forest-labs/FLUX.2-klein-4B