Pith. sign in

REVIEW 5 cited by

The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization

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 2312.08872 v4 pith:QJZBSAHN submitted 2023-12-13 cs.CV

Jiafeng Mao , Xueting Wang , Kiyoharu Aizawa This is my paper · ORCID
classification cs.CV
keywords imagesticketswinninginitialnoisegenerationtext-to-imagecontent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-to-image diffusion models allow users control over the content of generated images. Still, text-to-image generation occasionally leads to generation failure requiring users to generate dozens of images under the same text prompt before they obtain a satisfying result. We formulate the lottery ticket hypothesis in denoising: randomly initialized Gaussian noise images contain special pixel blocks (winning tickets) that naturally tend to be denoised into specific content independently. The generation failure in standard text-to-image synthesis is caused by the gap between optimal and actual spatial distribution of winning tickets in initial noisy images. To this end, we implement semantic-driven initial image construction creating initial noise from known winning tickets for each concept mentioned in the prompt. We conduct a series of experiments that verify the properties of winning tickets and demonstrate their generalizability across images and prompts. Our results show that aggregating winning tickets into the initial noise image effectively induce the model to generate the specified object at the corresponding location. Project Page: https://ut-mao.github.io/noise.github.io

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. Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Appearance pointers are compact tokens that let a diffusion transformer apply text, image, or combined prompts to specific image regions in a single pass.

  2. Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Z-Sampling alternates high-guidance denoising and low-guidance inversion at each step to improve prompt alignment in pretrained text-to-image diffusion models.

  3. A Noise is Worth Diffusion Guidance

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A one-step learned noise refinement replaces classifier-free guidance at inference on Stable Diffusion 2.1, giving comparable image quality at about 1.7x lower cost.

  4. All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Certain random seeds yield consistently more accurate compositional text-to-image outputs, and mining these seeds plus fine-tuning on the resulting self-generated images improves numerical and spatial composition accuracy.

  5. TKG-DM: Training-free Chroma Key Content Generation Diffusion Model

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Adjusting the mean of specific channels in the initial noise of Stable Diffusion produces foreground objects on a uniform, user-selected chroma key background without any fine-tuning.

Pith tools