# Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models

arXiv: https://arxiv.org/abs/2405.00760 · HTML: https://mlsanity.com/paper/2405.00760/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 37 of its 43 references that are in the map.
- First posted on arXiv 1 May 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)

## Built on by (most cited first, 30 of 59)

- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [Distribution Matching Distillation Meets Reinforcement Learning](https://mlsanity.com/paper/2511.13649/) (2025)
- [Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization](https://mlsanity.com/paper/2502.01051/) (2025)
- [DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2506.03517/) (2025)
- [Improving GFlowNets for Text-to-Image Diffusion Alignment](https://mlsanity.com/paper/2406.00633/) (2024)
- [DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling](https://mlsanity.com/paper/2412.00759/) (2024)
- [Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models](https://mlsanity.com/paper/2505.11245/) (2025)
- [Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models](https://mlsanity.com/paper/2605.10759/) (2026)
- [Improving Long-Text Alignment for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2410.11817/) (2024)
- [Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward](https://mlsanity.com/paper/2411.15247/) (2024)
- [Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models](https://mlsanity.com/paper/2511.16955/) (2025)
- [Video Generation Models Are Good Latent Reward Models](https://mlsanity.com/paper/2511.21541/) (2025)
- [SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization](https://mlsanity.com/paper/2412.05095/) (2024)
- [Aligning Few-Step Diffusion Models with Dense Reward Difference Learning](https://mlsanity.com/paper/2411.11727/) (2024)
- [Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design](https://mlsanity.com/paper/2507.00445/) (2025)
- [Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator](https://mlsanity.com/paper/2510.13454/) (2025)
- [Composition and Alignment of Diffusion Models using Constrained Learning](https://mlsanity.com/paper/2508.19104/) (2025)
- [MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models](https://mlsanity.com/paper/2510.01549/) (2025)
- [ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models](https://mlsanity.com/paper/2505.22569/) (2025)
- [Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2510.23974/) (2025)
- [Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data](https://mlsanity.com/paper/2503.21694/) (2025)
- [Towards Self-Improvement of Diffusion Models via Group Preference Optimization](https://mlsanity.com/paper/2505.11070/) (2025)
- [LongAnimation: Long Animation Generation with Dynamic Global-Local Memory](https://mlsanity.com/paper/2507.01945/) (2025)
- [Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models](https://mlsanity.com/paper/2602.03211/) (2026)
- [LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories](https://mlsanity.com/paper/2604.15311/) (2026)
- [High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning](https://mlsanity.com/paper/2503.22179/) (2025)
- [ContentV: Efficient Training of Video Generation Models with Limited Compute](https://mlsanity.com/paper/2506.05343/) (2025)
- [ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning](https://mlsanity.com/paper/2507.22604/) (2025)

## Abstract (arXiv)

Optimizing a text-to-image diffusion model with a given reward function is an important but underexplored research area. In this study, we propose Deep Reward Tuning (DRTune), an algorithm that directly supervises the final output image of a text-to-image diffusion model and back-propagates through the iterative sampling process to the input noise. We find that training earlier steps in the sampling process is crucial for low-level rewards, and deep supervision can be achieved efficiently and effectively by stopping the gradient of the denoising network input. DRTune is extensively evaluated on various reward models. It consistently outperforms other algorithms, particularly for low-level control signals, where all shallow supervision methods fail. Additionally, we fine-tune Stable Diffusion XL 1.0 (SDXL 1.0) model via DRTune to optimize Human Preference Score v2.1, resulting in the Favorable Diffusion XL 1.0 (FDXL 1.0) model. FDXL 1.0 significantly enhances image quality compared to SDXL 1.0 and reaches comparable quality compared with Midjourney v5.2.