OmniPrism: Learning Disentangled Visual Concept for Image Generation

[2412.12242] OmniPrism: Learning Disentangled Visual Concept for Image Generation Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2412.12242 (cs) [Submitted on 16 Dec 2024 ( v1 ), last revised 10 Apr 2026 (this version, v2)] Title: OmniPrism: Learning Disentangled Visual Concept for Image Generation Authors: Yangyang Li , Daqing Liu , Wu Liu , Allen He , Xinchen Liu , Yongdong Zhang , Guoqing Jin View a PDF of the paper titled OmniPrism: Learning Disentangled Visual Concept for Image Generation, by Yangyang Li and 6 other authors View PDF HTML (experimental) Abstract: Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily disrupted by irrelevant concepts in multi-aspect concept scenarios, leading to concept confusion and hindering creative generation. To address this, we propose OmniPrism, a visual concept disentangling approach for creative image generation. Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts. We utilize the rich semantic space of a multimodal extractor to achieve concept disentanglement from given images and concept guidance. To disentangle concepts with different semantics, we construct a paired concept disentangled dataset (PCD-200K), where each pair shares the same concept such as content, style, and composition. We learn disentangled concept representations through our contrastive orthogonal disentangled (COD) training pipeline, which are then injected into additional diffusion cross-attention layers for generation. A set of block embeddings is designed to adapt each block's concept domain in the diffusion models. Extensive experiments demonstrate that our method can generate high-quality, concept-disentangled results with high fidelity to text prompts and desired concepts. Comments: WebPage available at this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2412.12242 [cs.CV] (or arXiv:2412.12242v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2412.12242 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yangyang Li [ view email ] [v1] Mon, 16 Dec 2024 18:59:52 UTC (35,085 KB) [v2] Fri, 10 Apr 2026 10:12:32 UTC (41,706 KB) Full-text links: Access Paper: View a PDF of the paper titled OmniPrism: Learning Disentangled Visual Concept for Image Generation, by Yangyang Li and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2024-12 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation#219367
• Accelerating Masked Image Generation by Learning Controlled Latent Dynamics#925937
• Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation#1084232
• Neural specialization for 'visual' concepts emerges in the absence of vision.#3807
• Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation#14062