{"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/latte-latent-diffusion-transformer-for-video","title":"Latte: Latent Diffusion Transformer for Video Generation","arxiv_id":"2401.03048","date":"2024-01-05","proceeding":null,"authors":["Xin Ma","Yaohui Wang","Gengyun Jia","Xinyuan Chen","Ziwei Liu","Yuan-Fang Li","Cunjian Chen","Yu Qiao"],"abstract":"We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.","url_abs":"https://arxiv.org/abs/2401.03048v1","url_pdf":"https://arxiv.org/pdf/2401.03048v1.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":"latte-latent-diffusion-transformer-for-video","repo_url":"https://github.com/maxin-cn/Latte","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"latte-latent-diffusion-transformer-for-video","repo_url":"https://github.com/showlab/FAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"latte-latent-diffusion-transformer-for-video","repo_url":"https://github.com/vchitect/latte","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"latte-latent-diffusion-transformer-for-video","repo_url":"https://github.com/mindspore-lab/mindone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.03048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03048"}},"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/mindspore-lab/mindone","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vchitect/latte","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/showlab/FAR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maxin-cn/Latte","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_honours":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"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":0,"samples":[{"code_sha256_prefix":"72ee7e991255ed28","entry":"clip_grad_norm_","repo":"maxin-cn/Latte","repo_kind":"official","path":"utils.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72ee7e991255ed28"}},{"code_sha256_prefix":"ea2dc93d273c536c","entry":"create_logger","repo":"maxin-cn/Latte","repo_kind":"official","path":"train_pl.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/train_pl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea2dc93d273c536c"}},{"code_sha256_prefix":"c92c27c924b517e8","entry":"get_2d_sincos_pos_embed","repo":"maxin-cn/Latte","repo_kind":"official","path":"models/latte.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/models/latte.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c92c27c924b517e8"}},{"code_sha256_prefix":"f2b6bc25cb2bbec8","entry":"get_experiment_dir","repo":"maxin-cn/Latte","repo_kind":"official","path":"utils.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2b6bc25cb2bbec8"}},{"code_sha256_prefix":"8c9a5a9b54bc8e33","entry":"get_filelist","repo":"maxin-cn/Latte","repo_kind":"official","path":"datasets/ffs_datasets.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/datasets/ffs_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c9a5a9b54bc8e33"}},{"code_sha256_prefix":"64900e821beadb4e","entry":"get_grad_norm","repo":"maxin-cn/Latte","repo_kind":"official","path":"utils.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"64900e821beadb4e"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"maxin-cn/Latte","repo_kind":"official","path":"models/latte.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/models/latte.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"b76cb2065bce9c3e","entry":"numpy2tensor","repo":"maxin-cn/Latte","repo_kind":"official","path":"datasets/ffs_datasets.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/datasets/ffs_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b76cb2065bce9c3e"}},{"code_sha256_prefix":"2ce6782a49b98214","entry":"temporal_sampling","repo":"maxin-cn/Latte","repo_kind":"official","path":"datasets/ffs_datasets.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/datasets/ffs_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ce6782a49b98214"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"maxin-cn/Latte","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"129b804760b3115f"}},{"code_sha256_prefix":"6fe195fcfd10e259","entry":"checkpoint","repo":"maxin-cn/Latte","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6fe195fcfd10e259"}},{"code_sha256_prefix":"c8dc321d086803c8","entry":"get_1d_sincos_temp_embed","repo":"maxin-cn/Latte","repo_kind":"official","path":"models/latte.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/models/latte.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c8dc321d086803c8"}},{"code_sha256_prefix":"319f00691ca1b97c","entry":"timestep_embedding","repo":"maxin-cn/Latte","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/maxin-cn/Latte/blob/HEAD/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"319f00691ca1b97c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}