Pith. sign in

REVIEW 10 cited by

Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image 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 2405.14828 v2 pith:UYUDP433 submitted 2024-05-23 cs.CV

Katherine Xu , Lingzhi Zhang , Jianbo Shi This is my paper · ORCID
classification cs.CV
keywords seedsimageseeddiffusionimagesgoodinferencerandom
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent advances in text-to-image (T2I) diffusion models have facilitated creative and photorealistic image synthesis. By varying the random seeds, we can generate many images for a fixed text prompt. Technically, the seed controls the initial noise and, in multi-step diffusion inference, the noise used for reparameterization at intermediate timesteps in the reverse diffusion process. However, the specific impact of the random seed on the generated images remains relatively unexplored. In this work, we conduct a large-scale scientific study into the impact of random seeds during diffusion inference. Remarkably, we reveal that the best 'golden' seed achieved an impressive FID of 21.60, compared to the worst 'inferior' seed's FID of 31.97. Additionally, a classifier can predict the seed number used to generate an image with over 99.9% accuracy in just a few epochs, establishing that seeds are highly distinguishable based on generated images. Encouraged by these findings, we examined the influence of seeds on interpretable visual dimensions. We find that certain seeds consistently produce grayscale images, prominent sky regions, or image borders. Seeds also affect image composition, including object location, size, and depth. Moreover, by leveraging these 'golden' seeds, we demonstrate improved image generation such as high-fidelity inference and diversified sampling. Our investigation extends to inpainting tasks, where we uncover some seeds that tend to insert unwanted text artifacts. Overall, our extensive analyses highlight the importance of selecting good seeds and offer practical utility for image generation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Certain Gaussian initial noises act as winning tickets that bias motion diffusion toward specific semantics; retrieving and KL-refining them improves text-motion alignment without retraining.

  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. LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting

    cs.CV 2024-11 conditional novelty 6.0 of 10

    LumiNet transfers lighting between indoor scenes from images alone by conditioning a diffusion model on latent intrinsics from the source and a lighting code from the target.

  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.

  6. GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design

    cs.HC 2025-08 conditional novelty 5.0 of 10

    GenTune improves AI image refinement by tracing image regions back to prompt labels and allowing element-level, semantic-guided edits.

  7. OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection

    cs.CV 2025-07 reject novelty 5.0 of 10

    OptiPrune jointly optimizes initial noise via attention diagnostics and prunes similar tokens in self-attention, reporting marginal CLIP gains without latency measurements.

  8. Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Ctrl-Z Sampling improves text-to-image outputs by adaptively rolling back and re-exploring when a reward model flags a quality plateau, at roughly 3 to 9 times the usual compute.

  9. Pinterest Canvas: Large-Scale Image Generation at Pinterest

    cs.CV 2026-03 conditional novelty 4.0 of 10

    A FLUX-style base diffusion model plus task-specific fine-tunes and product-preserving pipelines yields double-digit Pinterest ads engagement lifts and higher no-defect rates than GPT-Image, FLUX Kontext, and Nano Banana.

  10. TryOffAnyone: Tiled Cloth Generation from a Dressed Person

    cs.CV 2024-12 reject novelty 4.0 of 10

    A mask-conditioned, Stable Diffusion-based model generates tiled garment images from dressed-person photos and reports best-seed metrics that improve on prior work but with a flawed evaluation protocol.

Pith tools