Instructions to use DirtScan/trail-delight-klein4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DirtScan/trail-delight-klein4b with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DirtScan/trail-delight-klein4b", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
DirtScan trail de-lighting (FLUX.2 Klein Base 4B LoRA)
LoRA weights used by Trail From Images to remove shadows and lighting from trail photos before texturing.
Use it with FLUX.2 Klein Base 4B, not the distilled Klein 4B. Download the
weights and the upstream models with scripts/download-delighting-models.sh
in the Trail From Images source.
Each Trail From Images release has a matching git tag in this repository.
Check downloads against SHA256SUMS.
- Downloads last month
- 51
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for DirtScan/trail-delight-klein4b
Base model
black-forest-labs/FLUX.2-klein-base-4B