Instructions to use BreakpointAI/boxnet-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BreakpointAI/boxnet-xl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BreakpointAI/boxnet-xl", 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
|
Download README.md from BreakpointAI/boxnet-xl: direct link, hf CLI and curl.
- Browser
- Download file 1.11 kB
-
https://huggingface.co/BreakpointAI/boxnet-xl/resolve/main/README.md
- Command line
-
hf download hf://BreakpointAI/boxnet-xl/README.md
-
curl -L -o README.md https://huggingface.co/BreakpointAI/boxnet-xl/resolve/main/README.md
1.11 kB
metadata
library_name: diffusers
license: other
license_name: research-use
tags:
- object-detection
- bounding-boxes
- grounding
- diffusion
- synthetic-data
boxnet-xl
SDXL-based UNet fine-tuned for grounded image generation.
Released by Breakpoint AI as part of open-sourcing the company's research artifacts.
| Training data | BreakpointAI/breakpoint-grounding-55m |
| Checkpoint step | 260,000 |
| Training run | W&B |
Contents
| Path | Size | What it is |
|---|---|---|
unet/ |
7.7 GB | SDXL UNet weights |
Inference weights only. Optimizer, LR scheduler, RNG and dataloader state were not uploaded, so this checkpoint cannot be used to resume training.
Citation
@misc{breakpoint_boxnet_xl,
title = {boxnet-xl},
author = {Wang, Franklin and Zhong, Desmond and Murdoch, Jamie},
year = {2026},
url = {https://huggingface.co/BreakpointAI/boxnet-xl}
}