Pith. sign in

REVIEW 11 cited by

Make It Count: Text-to-Image Generation with an Accurate Number of Objects

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 2406.10210 v1 pith:NM4GBY2M submitted 2024-06-14 cs.CV cs.AIcs.GR

Lital Binyamin , Yoad Tewel , Hilit Segev , Eran Hirsch , Royi Rassin , Gal Chechik This is my paper · ORCID
classification cs.CVcs.AIcs.GR
keywords objectmodelobjectscountdiffusiongenerationcarrycountgen
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications from technical documents, to children's books to illustrating cooking recipes. Generating object-correct counts is fundamentally challenging because the generative model needs to keep a sense of separate identity for every instance of the object, even if several objects look identical or overlap, and then carry out a global computation implicitly during generation. It is still unknown if such representations exist. To address count-correct generation, we first identify features within the diffusion model that can carry the object identity information. We then use them to separate and count instances of objects during the denoising process and detect over-generation and under-generation. We fix the latter by training a model that predicts both the shape and location of a missing object, based on the layout of existing ones, and show how it can be used to guide denoising with correct object count. Our approach, CountGen, does not depend on external source to determine object layout, but rather uses the prior from the diffusion model itself, creating prompt-dependent and seed-dependent layouts. Evaluated on two benchmark datasets, we find that CountGen strongly outperforms the count-accuracy of existing baselines.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

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

  1. FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    FlowMo reduces temporal artifacts in video generation by guiding the denoising process to lower the maximum patch-wise variance of consecutive-frame differences in the latent space.

  2. Be Decisive: Noise-Induced Layouts for Multi-Subject Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A layout-free method that predicts subject regions from initial noise and refines them via guidance, improving multi-subject prompt alignment and layout diversity.

  3. ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ISAC improves multi-instance image generation by carving out instance regions from self-attention first and then assigning semantics to those regions.

  4. Towards Self-Improvement of Diffusion Models via Group Preference Optimization

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Group Preference Optimization (GPO) uses standardized rewards over self-generated image groups to improve diffusion models' counting, text rendering, and prompt alignment without human preference annotations.

  5. InstanceGen: Image Generation with Instance-level Instructions

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A training-free pipeline that uses attention-derived instance masks and LLM-assigned per-segment instructions to improve multi-object, multi-attribute text-to-image generation.

  6. Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers

    cs.CV 2025-05 reject novelty 6.0 of 10

    LayouSyn is a text-to-layout pipeline using a lightweight open-source LLM for object extraction and an aspect-aware diffusion Transformer for bounding-box generation, reporting SOTA on NSR-1K and COCO-GR layout metrics.

  7. Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A training-free method that repairs ambiguous cross-attention in MMDiT text-to-image models, using block and text-encoder alignment losses and a back-to-start sampling strategy, substantially improving multi-similar-s...

  8. Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A probabilistic overlap measure for object positions yields a human-aligned spatial relationship metric and a training-free generation guidance method for text-to-image models.

  9. Cost-Aware Routing for Efficient Text-To-Image Generation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A cost-aware router selects per prompt the best among nine pre-trained text-to-image models, beating every single model on the quality-versus-cost frontier.

  10. JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models

    cs.CV 2025-05 conditional novelty 5.0 of 10

    JEDI minimizes Jensen-Shannon divergence between subject attention maps during diffusion sampling, reducing attribute mixing in generated images.

  11. CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion

    cs.CV 2025-05 reject novelty 5.0 of 10

    CountDiffusion improves object-count accuracy in text-to-image diffusion by detecting objects in a one-step predicted image and applying attention-map guidance to add or remove instances.

Pith tools