{"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/phyt2v-llm-guided-iterative-self-refinement","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","arxiv_id":"2412.00596","date":"2024-11-30","proceeding":"CVPR 2025 1","authors":["Qiyao Xue","Xiangyu Yin","Boyuan Yang","Wei Gao"],"abstract":"Text-to-video (T2V) generation has been recently enabled by transformer-based diffusion models, but current T2V models lack capabilities in adhering to the real-world common knowledge and physical rules, due to their limited understanding of physical realism and deficiency in temporal modeling. Existing solutions are either data-driven or require extra model inputs, but cannot be generalizable to out-of-distribution domains. In this paper, we present PhyT2V, a new data-independent T2V technique that expands the current T2V model's capability of video generation to out-of-distribution domains, by enabling chain-of-thought and step-back reasoning in T2V prompting. Our experiments show that PhyT2V improves existing T2V models' adherence to real-world physical rules by 2.3x, and achieves 35% improvement compared to T2V prompt enhancers. The source codes are available at: https://github.com/pittisl/PhyT2V.","url_abs":"https://arxiv.org/abs/2412.00596v2","url_pdf":"https://arxiv.org/pdf/2412.00596v2.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":"phyt2v-llm-guided-iterative-self-refinement","repo_url":"https://github.com/pittisl/phyt2v","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"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.00596","atlas_url":"https://app.syntology.ai/?focus=2412.00596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00596"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/pittisl/phyt2v","reach":{"status":"ok"}}],"summary":{"unverified":16},"by_repo_kind":{"official":{"samples":16,"ran":0,"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":16,"samples":[{"code_sha256_prefix":"02c48da3e29b7180","entry":"compute_prompt_embeddings","repo":"pittisl/phyt2v","repo_kind":"official","path":"finetune/train_cogvideox_lora.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/finetune/train_cogvideox_lora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02c48da3e29b7180"}},{"code_sha256_prefix":"407efac283ca64e0","entry":"conv","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/gradio_composite_demo/rife/IFNet.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/gradio_composite_demo/rife/IFNet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"407efac283ca64e0"}},{"code_sha256_prefix":"3f2fc3183e384950","entry":"convert_prompt","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/convert_demo.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/convert_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f2fc3183e384950"}},{"code_sha256_prefix":"55cbe394bd642f3b","entry":"convert_prompt","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/gradio_web_demo.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/gradio_web_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55cbe394bd642f3b"}},{"code_sha256_prefix":"48ae7f74e7480412","entry":"deconv","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/gradio_composite_demo/rife/IFNet.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/gradio_composite_demo/rife/IFNet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48ae7f74e7480412"}},{"code_sha256_prefix":"e1f46e5593d36bb6","entry":"encode_prompt","repo":"pittisl/phyt2v","repo_kind":"official","path":"finetune/train_cogvideox_lora.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/finetune/train_cogvideox_lora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e1f46e5593d36bb6"}},{"code_sha256_prefix":"26e0ce3a784d8f9d","entry":"enhanced_prompt","repo":"pittisl/phyt2v","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/prompts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26e0ce3a784d8f9d"}},{"code_sha256_prefix":"e8653493c0e3da07","entry":"image_to_url","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/convert_demo.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/convert_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8653493c0e3da07"}},{"code_sha256_prefix":"44d67662b32e0a93","entry":"make_inference","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/gradio_composite_demo/rife_model.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/gradio_composite_demo/rife_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44d67662b32e0a93"}},{"code_sha256_prefix":"2841d720c3626d9a","entry":"mismatch_prompt","repo":"pittisl/phyt2v","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/prompts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2841d720c3626d9a"}},{"code_sha256_prefix":"371391555c7fdb5b","entry":"pad_image","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/gradio_composite_demo/rife_model.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/gradio_composite_demo/rife_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"371391555c7fdb5b"}},{"code_sha256_prefix":"942a8e1e916973d3","entry":"pc_score_generation","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"942a8e1e916973d3"}},{"code_sha256_prefix":"2d91484795ce244a","entry":"physical_law_prompt","repo":"pittisl/phyt2v","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/prompts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d91484795ce244a"}},{"code_sha256_prefix":"e850d74a6f50e46f","entry":"process_one","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e850d74a6f50e46f"}},{"code_sha256_prefix":"ac6e32b63611104f","entry":"sa_score_generation","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac6e32b63611104f"}},{"code_sha256_prefix":"f104145895788f8e","entry":"save_video","repo":"pittisl/phyt2v","repo_kind":"official","path":"inference/gradio_web_demo.py","file_url":"https://github.com/pittisl/phyt2v/blob/HEAD/inference/gradio_web_demo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f104145895788f8e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}