Pith. sign in

REVIEW 17 cited by

LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models

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 2404.11098 v4 pith:LJ4WEIRO submitted 2024-04-17 cs.CV

Dingkun Zhang , Sijia Li , Chen Chen , Qingsong Xie , Haonan Lu This is my paper · ORCID
classification cs.CV
keywords layerpruningdistillationproposeddiffusionmodelscompressingfeature
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In the era of AIGC, the demand for low-budget or even on-device applications of diffusion models emerged. In terms of compressing the Stable Diffusion models (SDMs), several approaches have been proposed, and most of them leveraged the handcrafted layer removal methods to obtain smaller U-Nets, along with knowledge distillation to recover the network performance. However, such a handcrafting manner of layer removal is inefficient and lacks scalability and generalization, and the feature distillation employed in the retraining phase faces an imbalance issue that a few numerically significant feature loss terms dominate over others throughout the retraining process. To this end, we proposed the layer pruning and normalized distillation for compressing diffusion models (LAPTOP-Diff). We, 1) introduced the layer pruning method to compress SDM's U-Net automatically and proposed an effective one-shot pruning criterion whose one-shot performance is guaranteed by its good additivity property, surpassing other layer pruning and handcrafted layer removal methods, 2) proposed the normalized feature distillation for retraining, alleviated the imbalance issue. Using the proposed LAPTOP-Diff, we compressed the U-Nets of SDXL and SDM-v1.5 for the most advanced performance, achieving a minimal 4.0% decline in PickScore at a pruning ratio of 50% while the comparative methods' minimal PickScore decline is 8.2%.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 17 Pith papers

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

  1. TinyFusion: Diffusion Transformers Learned Shallow

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A learnable depth-pruning method that optimizes post-fine-tuning recoverability produces a 14-layer DiT-XL with FID 2.86 and a 2x speedup at 7% of the original training cost.

  2. Importance-Aware OBS Pruning for Diffusion Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Injecting spatial importance maps (e.g., CFG delta) into the OBS Hessian improves subject preservation in pruned diffusion models at high sparsity, but gains over the baseline are small and without error bars.

  3. CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation

    cs.AR 2026-07 conditional novelty 6.0 of 10

    Disaggregating cache operators from compute and overlapping them across the two classifier-free-guidance branches turns cross-timestep caching into up to 1.80x real end-to-end speedup on edge GPUs when the cache overf...

  4. DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

    cs.CV 2026-04 conditional novelty 6.0 of 10

    A learnable cost predictor plus dynamic programming allocates layer-wise token sparsity for diffusion transformers, removing forced full steps and cutting ~54% compute on PixArt-α without quality loss.

  5. ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ALTER jointly learns layer pruning masks and timestep-to-expert routing for diffusion UNets, cutting MACs to 26% of the 50-step baseline while keeping FID and CLIP scores near parity.

  6. TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    TCAQ-DM applies timestep-channel reparameterization, adaptive post-Softmax quantizer selection, and progressive aligned reconstruction to post-train quantize diffusion models down to W4A4 with usable FID.

  7. Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A bilevel training procedure that simultaneously restores a pruned diffusion model's quality and suppresses targeted concepts beats sequential fine-tuning followed by unlearning.

  8. SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

    cs.CV 2024-12 conditional novelty 6.0 of 10

    SnapGen is a 379M-parameter UNet with cross-architecture distillation and a 1.38M-parameter decoder that generates 1024x1024 images on a phone in about 1.4 seconds, with GenEval 0.66 and ImageNet FID 2.06.

  9. Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

    cs.CV 2024-11 conditional novelty 6.0 of 10

    CoDe speeds up Visual Auto-Regressive image generation by using a 2B model for early coarse scales and a 0.3B model for later fine scales, with 1.7x-2.9x speedup and only a small FID increase.

  10. Adversarial Diffusion Compression for Real-World Image Super-Resolution

    eess.IV 2024-11 conditional novelty 6.0 of 10

    AdcSR distills OSEDiff into a pruned diffusion-GAN that cuts inference time 3.7x and parameters 74% while achieving comparable super-resolution quality.

  11. One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models

    cs.CV 2025-05 conditional novelty 5.0 of 10

    TiUE shares one encoder pass across parallel decoder time steps in a distilled text-to-image student, improving one-step generation diversity while removing the iterative denoising loop.

  12. 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.

  13. Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model

    cs.CV 2025-01 conditional novelty 5.0 of 10

    CA-ToMe speeds up Stable Diffusion inference by adaptively merging similar tokens and caching merge pairs, reaching 6.09s average generation time with FID 34.05 on ImageNet.

  14. LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

    cs.LG 2024-12 conditional novelty 5.0 of 10

    LazyDiT learns small gates that decide when to reuse cached layer outputs, cutting diffusion transformer compute by up to half while matching or beating DDIM quality.

  15. Efficient Text-to-Audio Generation via Pruning

    eess.AS 2026-07 conditional novelty 4.0 of 10

    L1-norm filter pruning of AudioLDM's U-Net removes 83% of parameters and 39% of MACs, with quality maintained after 1M-step finetuning, but the comparison is confounded by unequal finetuning budgets.

  16. Diffusion Model Quantization: A Review

    cs.CV 2025-05 conditional novelty 3.0 of 10

    A structured review and benchmark of methods for quantizing diffusion models, with a taxonomy of post-training and quantization-aware approaches and an analysis of quantization artifacts.

  17. Efficient Diffusion Models: A Survey

    cs.LG 2025-02 conditional novelty 2.0 of 10

    The paper organizes research on efficient diffusion models into a taxonomy spanning algorithms, systems, and frameworks, and provides a curated reference list.

Pith tools