{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:16:10Z","timestamp":1777889770811,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01673","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18004-18013","source":"Crossref","is-referenced-by-count":0,"title":["Supercharged One-Step Text-to-Image Diffusion Models with Negative Prompts"],"prefix":"10.1109","author":[{"given":"Viet","family":"Nguyen","sequence":"first","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trung","family":"Dao","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khoi","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuong","family":"Pham","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toan","family":"Tran","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Tran","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Re-imagine the negative prompt algorithm: Transform 2d diffusion into 3d, alleviate janus problem and beyond","author":"Armandpour","year":"2023","journal-title":"ArXiv"},{"key":"ref2","volume-title":"AUTOMATIC1111. Automatic1111\/stable-diffusion-webui","year":"2025"},{"key":"ref3","article-title":"ediff-i: Text-to-image diffusion models with ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_12"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref7","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref9","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref10","volume-title":"Civitai Platform"},{"key":"ref11","volume-title":"comfyanonymous. comfyanonymous\/comfyui","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_11"},{"key":"ref13","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024","journal-title":"ArXiv"},{"key":"ref15","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"ArXiv"},{"key":"ref16","first-page":"27","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Prompt-to-prompt image editing with cross attention control.(2022)","volume-title":"International Conference on Learning Representations","author":"Hertz","year":"2023"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref20","first-page":"33","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume":"abs\/2301.12661","author":"Huang","year":"2023","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref24","article-title":"Noise-free score distillation","author":"Katzir","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","volume-title":"Flux","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref28","article-title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","volume-title":"11lyasviel. 1llyasviel\/stable-diffusion-webui-forge","year":"2025"},{"key":"ref30","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"ref31","article-title":"Latent consistency models: Synthesizing highresolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"You only sample once: Taming one-step text-to-image synthesis by self-cooperative diffusion gans","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Rethinking score distillation as a bridge between image distributions","volume":"abs\/2406.09417","author":"McAllister","year":"2024","journal-title":"ArXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00746"},{"key":"ref35","article-title":"Optimizing negative prompts for enhanced aesthetics and fidelity in text-to-image generation","author":"Ogezi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"International Conference on Learning Representations","author":"Podell","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.14988"},{"key":"ref38","article-title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Adversarial diffusion distillation","author":"Sauer","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref43","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref44","article-title":"JourneyDB: A benchmark for generative image understanding","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Sun","year":"2023"},{"key":"ref45","first-page":"36","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","article-title":"Enhancing mmdit-based text-to-image models for similar subject generation","author":"Wei","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","volume-title":"Stable diffusion 2.0 and the importance of negative prompts for good results","author":"Woolf","year":"2023"},{"key":"ref48","article-title":"Human preference score v 2: A solid benchmark for evaluating human preferences of text-to-image synthesis","volume":"abs\/2306.09341","author":"Wu","year":"2023","journal-title":"ArXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref50","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","volume":"abs\/2408.06072","author":"Yang","year":"2024","journal-title":"ArXiv"},{"key":"ref51","article-title":"Improved distribution matching distillation for fast image synthesis","author":"Yin","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02138"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445192.pdf?arnumber=11445192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:21Z","timestamp":1777612761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01673","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}