Pith. sign in

REVIEW 20 cited by

Adversarial Diffusion Distillation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.17042 v1 pith:V4NPFM3B submitted 2023-11-28 cs.CV

Axel Sauer , Dominik Lorenz , Andreas Blattmann , Robin Rombach This is my paper · ORCID
classification cs.CV
keywords diffusionimagemodelsadversarialdistillationstepshighhttps
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal in combination with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps. Our analyses show that our model clearly outperforms existing few-step methods (GANs, Latent Consistency Models) in a single step and reaches the performance of state-of-the-art diffusion models (SDXL) in only four steps. ADD is the first method to unlock single-step, real-time image synthesis with foundation models. Code and weights available under https://github.com/Stability-AI/generative-models and https://huggingface.co/stabilityai/ .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models

    cs.CV 2026-08 conditional novelty 7.0 of 10

    A temporal-spatial LSB mask over one shared weight buffer lets diffusion models use lower bit precision in less sensitive denoising stages, cutting compute by 25-50% on bit-serial hardware with no loss in image quality.

  2. A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

    cs.CV 2026-07 conditional novelty 6.5 of 10

    A three-layer perturbation probe shows latent selectivity is a near-binary rectified-flow fingerprint that survives ADD distillation, while score selectivity tracks distillation objective across 23 T2I models.

  3. Diagnosing Under-Development of Irreversible Processes in Video Generation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Text-to-video generators under-develop irreversible processes: near-zero progress and 92-100% stasis versus real footage (rho=+0.40, 35% static), confirmed by human raters.

  4. Parallel Decoding Distillation for Fast Image and Video Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A trajectory-based distillation method trains a student to predict multiple mean velocities per network evaluation, enabling 4-8 step generation with competitive quality and improved diversity.

  5. DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Selective reuse of composed attention states across denoising steps lets DiTango skip both remote KV communication and attention compute for low-contribution sequence partitions, cutting multi-GPU diffusion latency by...

  6. Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    CACFM applies RL to adaptively select critical regions in probability flow ODE trajectories for consistency distillation, yielding SOTA few-step results on FLUX and SDXL.

  7. Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    Implicit generative choices in diffusion models for ambiguous prompts are localized principally in self-attention layers, enabling a targeted ICM steering method that outperforms prior debiasing approaches.

  8. Na\"ive PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A lightweight predictor ranks initial noises by expected human-preference score for a prompt, selecting the best few for diffusion generation and reporting prompt difficulty.

  9. Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Category-level retrieval improves when text queries are converted into multiple generated images, aggregated with a learned attention module, and fused with CLIP text similarity.

  10. UNICE: Training A Universal Image Contrast Enhancer

    cs.CV 2025-07 conditional novelty 6.0 of 10

    UNICE trains a two-stage model to generate and fuse a pseudo multi-exposure sequence from one image, generalizing across four contrast-enhancement tasks without human labels.

  11. Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Fine-tuning a pretrained diffusion model with a GAN objective and most weights frozen yields a one-step generator that matches or beats prior distillation methods on several datasets.

  12. LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A learned distribution prior, predicted by a VAE-style decoder, lets flow-matching image models generate in fewer ODE steps than with a Gaussian prior.

  13. Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A three-stage pipeline combining sparse 'tile' attention with multi-step consistency distillation makes Open-Sora-Plan video generation up to 7.8x faster while keeping the aggregate VBench final score within 1%.

  14. Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Across four NAS/DNN-predictor regression benchmarks, GEN (deep graph convolution) achieves the best average rank over 11 GNN message-passing layers, though attention GATv2 wins on the largest graphs.

  15. MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scale

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A cascaded, segmentation-conditioned, per-instance diffusion method synthesizes globally coherent gigapixel microscopic detail from a phone photo and sparse microscope references at up to 350×.

  16. Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A compact 4B image generation/editing system with a fast one-step VAE, native-resolution packing, RL alignment, and 4-step distillation reports competitive benchmarks against 6B–80B open models.

  17. On the Redundancy of Timestep Embeddings in Diffusion Models

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Under high-dimensional concentration conditions, the diffusion denoising objective admits the same global minimizer without timestep embeddings, and time-agnostic U-Nets/DiTs empirically match or improve FID on CelebA...

  18. SD-Acc: Accelerating Stable Diffusion through Phase-aware Sampling and Hardware Co-Optimizations

    cs.AR 2025-07 conditional novelty 5.0 of 10

    Phase-aware sampling cuts Stable Diffusion's compute by roughly 2.4x to 5.7x with only small CLIP-score changes, and the accompanying FPGA accelerator turns this into 2.7x to 6.0x energy savings over an Nvidia V100 GPU.

  19. Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

    cs.LG 2025-05 conditional novelty 5.0 of 10

    ScaleKV cuts KV cache memory for Visual Autoregressive text-to-image generation to 10% by classifying layers as drafters or refiners per scale and pruning low-attention tokens while keeping benchmark scores nearly unchanged.

  20. Learning from Limited and Imperfect Data

    cs.LG 2025-07 unverdicted novelty 3.0 of 10

    A doctoral thesis compiling nine peer-reviewed papers on long-tailed image generation, long-tailed recognition, semi-supervised learning, and domain adaptation.

Pith tools