Pith. sign in

REVIEW 5 cited by

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

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 2406.02347 v3 pith:AUUGQNFH submitted 2024-06-04 cs.CV cs.AIcs.LG

Clément Chadebec , Onur Tasar , Eyal Benaroche , Benjamin Aubin This is my paper · ORCID
classification cs.CVcs.AIcs.LG
keywords diffusiongenerationmethodimagestepsflashseveralwhile
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score for few steps image generation on the COCO2014 and COCO2017 datasets, while requiring only several GPU hours of training and fewer trainable parameters than existing methods. In addition to its efficiency, the versatility of the method is also exposed across several tasks such as text-to-image, inpainting, face-swapping, super-resolution and using different backbones such as UNet-based denoisers (SD1.5, SDXL) or DiT (Pixart-$\alpha$), as well as adapters. In all cases, the method allowed to reduce drastically the number of sampling steps while maintaining very high-quality image generation. The official implementation is available at https://github.com/gojasper/flash-diffusion.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. 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.

  2. Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A new adversarial distribution matching loss for diffusion distillation gives one-step and few-step generators that match or exceed prior distillation methods on SDXL, SD3, and CogVideoX.

  3. The Hidden Cost of an Image: Quantifying the Energy Consumption of AI Image Generation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Energy consumption varies up to 46x across 17 diffusion models, quantization often increases rather than decreases energy use, and high image quality does not require high energy consumption.

  4. Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions

    cs.CV 2025-04 conditional novelty 6.0 of 10

    Diffusion models can keep most of their image quality after swapping global self-attention for a distilled multi-scale convolutional block, with FLOPs claimed to fall by up to 6929 times at 16K resolution.

  5. Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples

    cs.LG 2024-11 conditional novelty 6.0 of 10

    Directly supervising a consistency model against an ODE solver lowers ODE solving error yet degrades image quality, so better ODE solving does not imply better samples.

Pith tools