# SD-πXL: Generating Low-Resolution Quantized Imagery via Score Distillation

arXiv: https://arxiv.org/abs/2410.06236 · HTML: https://mlsanity.com/paper/2410.06236/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 83 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [Text-to-3D with Classifier Score Distillation](https://mlsanity.com/paper/2310.19415/) (2023)
- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Word-As-Image for Semantic Typography](https://mlsanity.com/paper/2303.01818/) (2023)
- [CLIPasso: Semantically-Aware Object Sketching](https://mlsanity.com/paper/2202.05822/) (2022)
- [Control3D: Towards Controllable Text-to-3D Generation](https://mlsanity.com/paper/2311.05461/) (2023)
- [Generative Escher Meshes](https://mlsanity.com/paper/2309.14564/) (2023)
- [Computational LEGO Technic Design](https://mlsanity.com/paper/2007.02245/) (2020)
- [Generating Pixel Art Character Sprites using GANs](https://mlsanity.com/paper/2208.06413/) (2022)

## Built on by (most cited first, 3 of 3)

- [Hand-Shadow Poser](https://mlsanity.com/paper/2505.07012/) (2025)
- [Voxify3D: Pixel Art Meets Volumetric Rendering](https://mlsanity.com/paper/2512.07834/) (2025)
- [Single-Line Drawing Generation via Semantics-Driven Optimization](https://mlsanity.com/paper/2606.01910/) (2026)

## Abstract (arXiv)

Low-resolution quantized imagery, such as pixel art, is seeing a revival in modern applications ranging from video game graphics to digital design and fabrication, where creativity is often bound by a limited palette of elemental units. Despite their growing popularity, the automated generation of quantized images from raw inputs remains a significant challenge, often necessitating intensive manual input. We introduce SD-πXL, an approach for producing quantized images that employs score distillation sampling in conjunction with a differentiable image generator. Our method enables users to input a prompt and optionally an image for spatial conditioning, set any desired output size H × W, and choose a palette of n colors or elements. Each color corresponds to a distinct class for our generator, which operates on an H × W × n tensor. We adopt a softmax approach, computing a convex sum of elements, thus rendering the process differentiable and amenable to backpropagation. We show that employing Gumbel-softmax reparameterization allows for crisp pixel art effects. Unique to our method is the ability to transform input images into low-resolution, quantized versions while retaining their key semantic features. Our experiments validate SD-πXL's performance in creating visually pleasing and faithful representations, consistently outperforming the current state-of-the-art. Furthermore, we showcase SD-πXL's practical utility in fabrication through its applications in interlocking brick mosaic, beading and embroidery design.