# Few-Step Diffusion via Score identity Distillation arXiv: https://arxiv.org/abs/2505.12674 ยท HTML: https://mlsanity.com/paper/2505.12674/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. - Builds on 66 of its 70 references that are in the map. - First posted on arXiv 19 May 2025. ## Placed in - Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/) ## Builds on (most cited first, 30 of 66) - [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) - [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021) - [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) - [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021) - [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019) - [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022) - [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021) - [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022) - [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022) - [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022) - [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023) - [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022) - [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022) - [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023) - [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022) - [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022) - [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023) - [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023) - [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022) - [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022) - [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021) ## Built on by (most cited first, 12 of 12) - [DLM-One: Diffusion Language Models for One-Step Sequence Generation](https://mlsanity.com/paper/2506.00290/) (2025) - [Score Distillation of Flow Matching Models](https://mlsanity.com/paper/2509.25127/) (2025) - [Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings](https://mlsanity.com/paper/2509.22925/) (2025) - [Continuous-Time Distribution Matching for Few-Step Diffusion Distillation](https://mlsanity.com/paper/2605.06376/) (2026) - [Beyond Scores: Proximal Diffusion Models](https://mlsanity.com/paper/2507.08956/) (2025) - [Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers](https://mlsanity.com/paper/2603.27666/) (2026) - [SPID: Distilled Protein Backbone Generation](https://mlsanity.com/paper/2510.03095/) (2025) - [One-step Diffusion Models with Bregman Density Ratio Matching](https://mlsanity.com/paper/2510.16983/) (2025) - [Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation](https://mlsanity.com/paper/2603.19570/) (2026) - [Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment](https://mlsanity.com/paper/2606.01651/) (2026) - [Structured Residual Connectivity Matters for Diffusion Transformers](https://mlsanity.com/paper/2609.33203/) (2026) - [Data-free Multistep Diffusion Distillation](https://mlsanity.com/paper/2610.19305/) (2026) ## Abstract (arXiv) Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models by distilling a pretrained score network into a one- or few-step generator. While existing methods have made notable progress, they often rely on real or teacher-synthesized images to perform well when distilling high-resolution T2I diffusion models such as Stable Diffusion XL (SDXL), and their use of classifier-free guidance (CFG) introduces a persistent trade-off between text-image alignment and generation diversity. We address these challenges by optimizing Score identity Distillation (SiD) -- a data-free, one-step distillation framework -- for few-step generation. Backed by theoretical analysis that justifies matching a uniform mixture of outputs from all generation steps to the data distribution, our few-step distillation algorithm avoids step-specific networks and integrates seamlessly into existing pipelines, achieving state-of-the-art performance on SDXL at 1024x1024 resolution. To mitigate the alignment-diversity trade-off when real text-image pairs are available, we introduce a Diffusion GAN-based adversarial loss applied to the uniform mixture and propose two new guidance strategies: Zero-CFG, which disables CFG in the teacher and removes text conditioning in the fake score network, and Anti-CFG, which applies negative CFG in the fake score network. This flexible setup improves diversity without sacrificing alignment. Comprehensive experiments on SD1.5 and SDXL demonstrate state-of-the-art performance in both one-step and few-step generation settings, along with robustness to the absence of real images. Our efficient PyTorch implementation, along with the resulting one- and few-step distilled generators, will be released publicly as a separate branch at https://github.com/mingyuanzhou/SiD-LSG.