{"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/streamingt2v-consistent-dynamic-and","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","arxiv_id":"2403.14773","date":"2024-03-21","proceeding":"CVPR 2025 1","authors":["Roberto Henschel","Levon Khachatryan","Hayk Poghosyan","Daniil Hayrapetyan","Vahram Tadevosyan","Zhangyang Wang","Shant Navasardyan","Humphrey Shi"],"abstract":"Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video generation (typically 16 or 24 frames), ending up with hard-cuts when naively extended to the case of long video synthesis. To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions. The key components are:(i) a short-term memory block called conditional attention module (CAM), which conditions the current generation on the features extracted from the previous chunk via an attentional mechanism, leading to consistent chunk transitions, (ii) a long-term memory block called appearance preservation module, which extracts high-level scene and object features from the first video chunk to prevent the model from forgetting the initial scene, and (iii) a randomized blending approach that enables to apply a video enhancer autoregressively for infinitely long videos without inconsistencies between chunks. Experiments show that StreamingT2V generates high motion amount. In contrast, all competing image-to-video methods are prone to video stagnation when applied naively in an autoregressive manner. Thus, we propose with StreamingT2V a high-quality seamless text-to-long video generator that outperforms competitors with consistency and motion. Our code will be available at: https://github.com/Picsart-AI-Research/StreamingT2V","url_abs":"https://arxiv.org/abs/2403.14773v2","url_pdf":"https://arxiv.org/pdf/2403.14773v2.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":"streamingt2v-consistent-dynamic-and","repo_url":"https://github.com/picsart-ai-research/streamingt2v","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.14773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14773"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/picsart-ai-research/streamingt2v","reach":{"status":"ok"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"55e0040242e9c1c7","entry":"retrieve_latents","repo":"picsart-ai-research/streamingt2v","repo_kind":"official","path":"code/i2v_enhance/pipeline_i2vgen_xl.py","file_url":"https://github.com/picsart-ai-research/streamingt2v/blob/HEAD/code/i2v_enhance/pipeline_i2vgen_xl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55e0040242e9c1c7"}},{"code_sha256_prefix":"f18101a2aaab565a","entry":"vfi_process","repo":"picsart-ai-research/streamingt2v","repo_kind":"official","path":"code/i2v_enhance/i2v_enhance_interface.py","file_url":"https://github.com/picsart-ai-research/streamingt2v/blob/HEAD/code/i2v_enhance/i2v_enhance_interface.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f18101a2aaab565a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}