{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/skyreels-a2-compose-anything-in-video","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","arxiv_id":"2504.02436","date":"2025-04-03","proceeding":null,"authors":["Zhengcong Fei","Debang Li","Di Qiu","Jiahua Wang","Yikun Dou","Rui Wang","Jingtao Xu","Mingyuan Fan","Guibin Chen","Yang Li","Yahui Zhou"],"abstract":"This paper presents SkyReels-A2, a controllable video generation framework capable of assembling arbitrary visual elements (e.g., characters, objects, backgrounds) into synthesized videos based on textual prompts while maintaining strict consistency with reference images for each element. We term this task elements-to-video (E2V), whose primary challenges lie in preserving the fidelity of each reference element, ensuring coherent composition of the scene, and achieving natural outputs. To address these, we first design a comprehensive data pipeline to construct prompt-reference-video triplets for model training. Next, we propose a novel image-text joint embedding model to inject multi-element representations into the generative process, balancing element-specific consistency with global coherence and text alignment. We also optimize the inference pipeline for both speed and output stability. Moreover, we introduce a carefully curated benchmark for systematic evaluation, i.e, A2 Bench. Experiments demonstrate that our framework can generate diverse, high-quality videos with precise element control. SkyReels-A2 is the first open-source commercial grade model for the generation of E2V, performing favorably against advanced closed-source commercial models. We anticipate SkyReels-A2 will advance creative applications such as drama and virtual e-commerce, pushing the boundaries of controllable video generation.","url_abs":"https://arxiv.org/abs/2504.02436v1","url_pdf":"https://arxiv.org/pdf/2504.02436v1.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":"skyreels-a2-compose-anything-in-video","repo_url":"https://github.com/skyworkai/skyreels-a2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"human-domain-subject-to-video","task_name":"Human-Domain Subject-to-Video"},{"task_slug":"open-domain-subject-to-video","task_name":"Open-Domain Subject-to-Video"},{"task_slug":"single-domain-subject-to-video","task_name":"Single-Domain Subject-to-Video"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-subject-to-video-on-opens2v-eval","task":"Open-Domain Subject-to-Video","dataset":"OpenS2V-Eval","model":"SkyReels-A2-Wan2.1-14B-Preview","rank_in_archive_order":5,"of":10,"metrics":{"Aesthetics":"0.3940","FaceSim":"0.4595","GmeScore":"0.6454","Motion":"0.2560","NaturalScore":"0.6722","NexusScore":"0.4377","Total Score":"0.4961","Venue":"Open-Source"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.02436","atlas_url":"https://app.syntology.ai/?focus=2504.02436","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2504.02436"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2504.02436\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2504.02436"},"call":"get_concepts_for_paper(arxiv_id=\"2504.02436\")"}],"by_repo":[{"repo":"skyworkai/skyreels-a2","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"03975a253fe895ade55af688fc02df4e169d23cbb23319b8ad7a34ecb9185807","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}