Instructions to use OsamaAbdeljaber/photorealistic-wood-board-sdxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OsamaAbdeljaber/photorealistic-wood-board-sdxl 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("OsamaAbdeljaber/photorealistic-wood-board-sdxl", torch_dtype=torch.bfloat16, device_map="cuda") 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] - Notebooks
- Google Colab
- Kaggle
Photorealistic Wood Board SDXL Checkpoint
This repository contains the fine-tuned photorealistic checkpoint used by Board Generator to convert synthetic wood-board ring and fiber maps into RGB side-face images.
The checkpoint is a derivative of
stabilityai/stable-diffusion-xl-base-1.0.
It contains the Board Generator fine-tuned UNet weights and learned null
conditioning embedding. It does not include the original SDXL base model.
Files
config.json: Board Generator runtime configuration for this checkpoint.unet.safetensors: fine-tuned SDXL UNet weights.null_embed.safetensors: learned null conditioning embedding.LICENSE.md: CreativeML Open RAIL++-M license from the SDXL base model.
Download
From the Board Generator repository root:
pip install -U huggingface_hub
hf download OsamaAbdeljaber/photorealistic-wood-board-sdxl \
config.json unet.safetensors null_embed.safetensors \
--local-dir photorealistic_model_checkpoint
Board Generator also needs the original SDXL base model files locally:
hf download stabilityai/stable-diffusion-xl-base-1.0 \
model_index.json \
scheduler/scheduler_config.json \
unet/config.json \
unet/diffusion_pytorch_model.safetensors \
vae/config.json \
vae/diffusion_pytorch_model.safetensors \
--local-dir SDXL_model
Use With Board Generator
The expected local layout is:
Board Generator repo/
SDXL_model/
scheduler/scheduler_config.json
unet/config.json
unet/diffusion_pytorch_model.safetensors
vae/config.json
vae/diffusion_pytorch_model.safetensors
photorealistic_model_checkpoint/
config.json
unet.safetensors
null_embed.safetensors
Then install the photorealistic requirements and start Board Generator normally.
License And Attribution
This checkpoint is distributed under the CreativeML Open RAIL++-M license terms
because it is derived from stabilityai/stable-diffusion-xl-base-1.0.
Downstream users must comply with the OpenRAIL++ use-based restrictions. This repository does not grant rights to use Stability AI trademarks or imply endorsement by Stability AI.
Intended Use
This model is intended for research use in synthetic wood-board generation and wood-quality inspection workflows, especially as part of the Board Generator simulation pipeline.
It is not a general-purpose wood image generator and is not expected to perform well outside the Board Generator conditioning format.
- Downloads last month
- 33
Model tree for OsamaAbdeljaber/photorealistic-wood-board-sdxl
Base model
stabilityai/stable-diffusion-xl-base-1.0