# Inference-Time Loss-Guided Colour Preservation in Diffusion Sampling

arXiv: https://arxiv.org/abs/2601.17259 · HTML: https://mlsanity.com/paper/2601.17259/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 24 Jan 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [Color Conditional Generation with Sliced Wasserstein Guidance](https://mlsanity.com/paper/2503.19034/) (2025)
- [Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis](https://mlsanity.com/paper/2409.02429/) (2024)

## Abstract (arXiv)

Precise color control remains a persistent failure mode in text-to-image diffusion systems, particularly in design-oriented workflows where outputs must satisfy explicit, user-specified color targets. We present an inference-time, region-constrained color preservation method that steers a pretrained diffusion model without any additional training. Our approach combines (i) ROI-based inpainting for spatial selectivity, (ii) background-latent re-imposition to prevent color drift outside the ROI, and (iii) latent nudging via gradient guidance using a composite loss defined in CIE Lab and linear RGB. The loss is constructed to control not only the mean ROI color but also the tail of the pixelwise error distribution through CVaR-style and soft-maximum penalties, with a late-start gate and a time-dependent schedule to stabilize guidance across denoising steps. We show that mean-only baselines can satisfy average color constraints while producing perceptually salient local failures, motivating our distribution-aware objective. The resulting method provides a practical, training-free mechanism for targeted color adherence that can be integrated into standard Stable Diffusion inpainting pipelines.