{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/upgpt-universal-diffusion-model-for-person","title":"UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer","arxiv_id":"2304.08870","date":"2023-04-18","proceeding":null,"authors":["Soon Yau Cheong","Armin Mustafa","Andrew Gilbert"],"abstract":"Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person has a different appearance e.g. pose, face, and clothing, despite using the same text prompt. The appearance inconsistency makes T2I unsuitable for pose transfer. We address this by proposing a multimodal diffusion model that accepts text, pose, and visual prompting. Our model is the first unified method to perform all person image tasks - generation, pose transfer, and mask-less edit. We also pioneer using small dimensional 3D body model parameters directly to demonstrate new capability - simultaneous pose and camera view interpolation while maintaining the person's appearance.","url_abs":"https://arxiv.org/abs/2304.08870v2","url_pdf":"https://arxiv.org/pdf/2304.08870v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"upgpt-universal-diffusion-model-for-person","repo_url":"https://github.com/soon-yau/upgpt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"pose-transfer","task_name":"Pose Transfer"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"visual-prompting","task_name":"Visual Prompting"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-transfer-on-deep-fashion","task":"Pose Transfer","dataset":"Deep-Fashion","model":"UPGPT","rank_in_archive_order":12,"of":12,"metrics":{"FID":"9.427"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.08870","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}