Pith. sign in

REVIEW 17 cited by

Wuerstchen: An Efficient Architecture for Large-Scale 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 2306.00637 v2 pith:ORWB5U6T submitted 2023-06-01 cs.CV

Pablo Pernias , Dominic Rampas , Mats L. Richter , Christopher J. Pal , Marc Aubreville This is my paper · ORCID
classification cs.CV
keywords diffusionapproachimagelatentmodelsperformancetext-to-imageachieve
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce W\"urstchen, a novel architecture for text-to-image synthesis that combines competitive performance with unprecedented cost-effectiveness for large-scale text-to-image diffusion models. A key contribution of our work is to develop a latent diffusion technique in which we learn a detailed but extremely compact semantic image representation used to guide the diffusion process. This highly compressed representation of an image provides much more detailed guidance compared to latent representations of language and this significantly reduces the computational requirements to achieve state-of-the-art results. Our approach also improves the quality of text-conditioned image generation based on our user preference study. The training requirements of our approach consists of 24,602 A100-GPU hours - compared to Stable Diffusion 2.1's 200,000 GPU hours. Our approach also requires less training data to achieve these results. Furthermore, our compact latent representations allows us to perform inference over twice as fast, slashing the usual costs and carbon footprint of a state-of-the-art (SOTA) diffusion model significantly, without compromising the end performance. In a broader comparison against SOTA models our approach is substantially more efficient and compares favorably in terms of image quality. We believe that this work motivates more emphasis on the prioritization of both performance and computational accessibility.

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. 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.

  2. Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer

    cs.CV 2025-11 conditional novelty 6.0 of 10

    Expressing all RoPE positions on the query's grid ('one attention, one scale') plus a small boundary content-exchange step restores mixed-resolution diffusion generation that naive position interpolation destroys.

  3. Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    PDAF estimates a latent domain prior with a lightweight diffusion model and uses it to condition segmentation features, improving domain-generalized semantic segmentation on four unseen urban datasets.

  4. Efficient and Robust Semantic Image Communication via Stable Cascade

    eess.IV 2025-07 conditional novelty 6.0 of 10

    A Stable Cascade based semantic image communication system transmits a compact image embedding (0.29% of original size) over noisy channels and reconstructs images faster and with better perceptual quality than GESCO,...

  5. ComposeAnything: Composite Object Priors for Text-to-Image Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ComposeAnything generates composite object priors from LLM-generated 2.5D layouts and guides diffusion denoising, improving compositional fidelity in text-to-image generation.

  6. Multi-Group Proportional Representation for Text-to-Image Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    The authors apply the MPR metric (an integral probability metric) to text-to-image generation, derive tractable forms for linear and decision-tree function classes, and use it as a fine-tuning objective that reduces i...

  7. "I Know It When I See It": Mood Spaces for Connecting and Expressing Visual Concepts

    cs.CV 2025-04 conditional novelty 6.0 of 10

    A few-example Mood Space, learned by matching spectral affinity structure of DINO tokens and decoding to CLIP, lets users interpolate and analogize visual concepts with simple vector arithmetic.

  8. Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

    cs.CV 2025-04 conditional novelty 6.0 of 10

    An efficient text-to-video system produces 2K, 24 fps, 5-second videos with a 4B-parameter model by distilling a 13B teacher and guiding high-resolution generation with low-resolution features.

  9. E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling

    cs.CV 2024-12 reject novelty 6.0 of 10

    A stage-wise continuous autoregressive model with multistage flow matching gets large speedups on 256x256 ImageNet generation, but with a clear FID cost versus DiT and MAR.

  10. F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration

    cs.CV 2024-12 conditional novelty 6.0 of 10

    FaceQ, a new 12K-image benchmark with multi-dimensional human preference scores, reveals that existing quality metrics poorly match human judgment on AI-generated faces, and F-Eval, an instruction-tuned LMM, outperforms them.

  11. Importance-Based Token Merging for Efficient Image and Video Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A token-merging method that anchors computation on high-CFG-importance tokens improves generation quality at fixed inference speedups.

  12. Instant Preference Alignment for Text-to-Image Diffusion Models

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An MLLM-driven, training-free pipeline extracts preference keywords from a reference image and modulates diffusion cross-attention at global and regional levels for instant, multi-round preference-aligned image generation.

  13. Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models

    cs.CR 2025-08 unverdicted novelty 5.0 of 10

    The abstract claims that 10 poisoned samples can backdoor multiple text-to-image models with over 90% attack success and resistance to defenses, but the supplied body is a different paper.

  14. Instability in Diffusion ODEs: An Explanation for Inaccurate Image Reconstruction

    cs.LG 2025-06 reject novelty 5.0 of 10

    Diffusion reconstruction errors are explained by an instability of the probability-flow ODE: under sparsity assumptions, the chance of instability tends to one as image dimension grows.

  15. ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning

    cs.CV 2025-01 conditional novelty 5.0 of 10

    Using clinical metadata as text prompts in a diffusion prior yields 0.2 to 0.5 dB PSNR gains for compressed sensing MRI reconstruction, but the gains are inconsistent at some acceleration factors.

  16. Text to Image Generation and Editing: A Survey

    cs.CV 2025-05 conditional novelty 3.0 of 10

    A broad survey of text-to-image generation and editing research from 2021 to 2024, organized by architecture and comparison tables.

  17. Text-to-Image Synthesis: A Decade Survey

    cs.CV 2024-11 conditional novelty 1.0 of 10

    A decade-spanning survey categorizes over 440 text-to-image papers by architecture, research problem, dataset, and evaluation metric.

Pith tools