Instructions to use pradhaansbhat/Thinking-In-Boxes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pradhaansbhat/Thinking-In-Boxes 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("pradhaansbhat/Thinking-In-Boxes", 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
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- black-forest-labs/FLUX.1-Kontext-dev
|
| 7 |
+
pipeline_tag: image-to-image
|
| 8 |
+
tags:
|
| 9 |
+
- Generative Modeling
|
| 10 |
+
- Image Editing
|
| 11 |
+
- Geometric Editing
|
| 12 |
+
- 3D Vision
|
| 13 |
+
datasets:
|
| 14 |
+
- pradhaansbhat/Thinking-In-Boxes
|
| 15 |
+
library_name: diffusers
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# [NeurIPS-2026] Thinking in Boxes: 3D Editing in Real Images Made Easy
|
| 19 |
+
|
| 20 |
+
[**Pradhaan S Bhat**](https://pradhaansbhat.github.io/)<sup>1</sup><sup>∗</sup> · [**Naveen Chandra R**](https://www.linkedin.com/in/naveen-chandra-r-7230aa192)<sup>1</sup><sup>∗</sup> · [**Rishubh Parihar**](https://rishubhpar.github.io/)<sup>1</sup> · [**Vaibhav Vavilala**](https://www.linkedin.com/in/vaibhav-vavilala)<sup>2</sup> · [**R. Venkatesh Babu**](https://cds.iisc.ac.in/faculty/venky/)<sup>1</sup> · [**D.A. Forsyth**](http://luthuli.cs.uiuc.edu/~daf/) · [**Anand Bhattad**](https://anandbhattad.github.io/)<sup>4</sup>
|
| 21 |
+
|
| 22 |
+
<sup>1</sup> Indian Institute of Science
|
| 23 |
+
<sup>2</sup> Apple
|
| 24 |
+
<sup>3</sup> UIUC
|
| 25 |
+
<sup>4</sup> Johns Hopkins University
|
| 26 |
+
|
| 27 |
+
<sup>∗</sup> Equal Contribution
|
| 28 |
+
|
| 29 |
+
[](https://arxiv.org/abs/2606.20556)
|
| 30 |
+
[](https://thinking-in-boxes.github.io)
|
| 31 |
+
[](https://github.com/PradhaanSBhat/Thinking-In-Boxes)
|
| 32 |
+
[](https://huggingface.co/pradhaansbhat/Thinking-In-Boxes)
|
| 33 |
+
[](https://huggingface.co/datasets/pradhaansbhat/Thinking-In-Boxes)
|
| 34 |
+
[]()
|
| 35 |
+
|
| 36 |
+
This is the trained LoRA used in the paper **Thinking In Boxes: 3D Editing in Real Images Made Easy**.
|
| 37 |
+
|
| 38 |
+
Thinking-In-Boxes is an Image-to-Image Generative LoRA for `black-forest-labs/FLUX.1-Kontext-dev` trained for the task of Geometric Image Editing.
|
| 39 |
+
|
| 40 |
+
This LoRA is trained on the dataset here: https://huggingface.co/datasets/pradhaansbhat/Thinking-In-Boxes. Details of training are available in the supplementary section of the paper.
|
| 41 |
+
|
| 42 |
+
## Usage with Diffusers 🧨
|
| 43 |
+
|
| 44 |
+
Please refer to the [[GitHub Repository]](https://github.com/PradhaanSBhat/Thinking-In-Boxes) on setup, inference and training.
|
| 45 |
+
|
| 46 |
+
## Citation
|
| 47 |
+
|
| 48 |
+
If you find our work useful, please consider citing:
|
| 49 |
+
|
| 50 |
+
```bibtex
|
| 51 |
+
@misc{bhat2026thinkingboxes3dediting,
|
| 52 |
+
title = {Thinking in Boxes: 3D Editing in Real Images Made Easy},
|
| 53 |
+
author = {Pradhaan S Bhat and Naveen Chandra R and Rishubh Parihar and Vaibhav Vavilala and R. Venkatesh Babu and D. A. Forsyth and Anand Bhattad},
|
| 54 |
+
year = {2026},
|
| 55 |
+
eprint = {2606.20556},
|
| 56 |
+
archivePrefix = {arXiv},
|
| 57 |
+
primaryClass = {cs.CV},
|
| 58 |
+
url = {https://arxiv.org/abs/2606.20556}
|
| 59 |
+
}
|
| 60 |
+
```
|
| 61 |
+
---
|