# AceTone: Bridging Words and Colors for Conditional Image Grading

arXiv: https://arxiv.org/abs/2604.00530 · HTML: https://mlsanity.com/paper/2604.00530/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [Deep Photo Style Transfer](https://mlsanity.com/paper/1703.07511/) (2017)
- [Photorealistic Style Transfer via Wavelet Transforms](https://mlsanity.com/paper/1903.09760/) (2019)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement](https://mlsanity.com/paper/2204.13983/) (2022)
- [PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency](https://mlsanity.com/paper/2105.09180/) (2021)
- [JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent](https://mlsanity.com/paper/2506.17612/) (2025)
- [Neural Preset for Color Style Transfer](https://mlsanity.com/paper/2303.13511/) (2023)
- [NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement](https://mlsanity.com/paper/2306.11920/) (2023)
- [ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2504.10514/) (2025)
- [Deep Preset: Blending and Retouching Photos with Color Style Transfer](https://mlsanity.com/paper/2007.10701/) (2020)
- [Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models](https://mlsanity.com/paper/2510.02880/) (2025)
- [CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment](https://mlsanity.com/paper/2404.01123/) (2024)
- [SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer](https://mlsanity.com/paper/2506.13465/) (2025)
- [Color Transfer with Modulated Flows](https://mlsanity.com/paper/2503.19062/) (2025)
- [Efficient Neural Network Encoding for 3D Color Lookup Tables](https://mlsanity.com/paper/2412.15438/) (2024)

## Built on by (most cited first, 2 of 2)

- [GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation](https://mlsanity.com/paper/2605.19889/) (2026)
- [PrefLUT: Reusable and Refinable Personalized Color Editing from Pairwise Preferences](https://mlsanity.com/paper/2609.34133/) (2026)

## Abstract (arXiv)

Color affects how we interpret image style and emotion. Previous color grading methods rely on patch-wise recoloring or fixed filter banks, struggling to generalize across creative intents or align with human aesthetic preferences. In this study, we propose AceTone, the first approach that supports multimodal conditioned color grading within a unified framework. AceTone formulates grading as a generative color transformation task, where a model directly produces 3D-LUTs conditioned on text prompts or reference images. We develop a VQ-VAE based tokenizer which compresses a 3×323 LUT vector to 64 discrete tokens with Delta E<2 fidelity. We further build a large-scale dataset, AceTone-800K, and train a vision-language model to predict LUT tokens, followed by reinforcement learning to align outputs with perceptual fidelity and aesthetics. Experiments show that AceTone achieves state-of-the-art performance on both text-guided and reference-guided grading tasks, improving LPIPS by up to 50% over existing methods. Human evaluations confirm that AceTone's results are visually pleasing and stylistically coherent, demonstrating a new pathway toward language-driven, aesthetic-aligned color grading.