{"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/follow-your-pose-pose-guided-text-to-video","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","arxiv_id":"2304.01186","date":"2023-04-03","proceeding":null,"authors":["Yue Ma","Yingqing He","Xiaodong Cun","Xintao Wang","Siran Chen","Ying Shan","Xiu Li","Qifeng Chen"],"abstract":"Generating text-editable and pose-controllable character videos have an imperious demand in creating various digital human. Nevertheless, this task has been restricted by the absence of a comprehensive dataset featuring paired video-pose captions and the generative prior models for videos. In this work, we design a novel two-stage training scheme that can utilize easily obtained datasets (i.e.,image pose pair and pose-free video) and the pre-trained text-to-image (T2I) model to obtain the pose-controllable character videos. Specifically, in the first stage, only the keypoint-image pairs are used only for a controllable text-to-image generation. We learn a zero-initialized convolutional encoder to encode the pose information. In the second stage, we finetune the motion of the above network via a pose-free video dataset by adding the learnable temporal self-attention and reformed cross-frame self-attention blocks. Powered by our new designs, our method successfully generates continuously pose-controllable character videos while keeps the editing and concept composition ability of the pre-trained T2I model. The code and models will be made publicly available.","url_abs":"https://arxiv.org/abs/2304.01186v2","url_pdf":"https://arxiv.org/pdf/2304.01186v2.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":"follow-your-pose-pose-guided-text-to-video","repo_url":"https://github.com/mayuelala/followyourpose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"follow-your-pose-pose-guided-text-to-video","repo_url":"https://github.com/mayuelala/followyourcanvas","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.01186","atlas_url":"https://app.syntology.ai/?focus=2304.01186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01186"}},"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/mayuelala/followyourpose","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mayuelala/followyourcanvas","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"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":"475c5f441075c9f1","entry":"collate_fn","repo":"mayuelala/followyourpose","repo_kind":"official","path":"app_followyourpose.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/app_followyourpose.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"475c5f441075c9f1"}},{"code_sha256_prefix":"909b3b2b06e2eca0","entry":"conv_nd","repo":"mayuelala/followyourpose","repo_kind":"official","path":"followyourpose/models/unet_blocks.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/followyourpose/models/unet_blocks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"909b3b2b06e2eca0"}},{"code_sha256_prefix":"0b088617d5525751","entry":"get_noise_pred_single","repo":"mayuelala/followyourpose","repo_kind":"official","path":"followyourpose/util.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/followyourpose/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b088617d5525751"}},{"code_sha256_prefix":"fb032d6fa7e6196d","entry":"next_step","repo":"mayuelala/followyourpose","repo_kind":"official","path":"followyourpose/util.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/followyourpose/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb032d6fa7e6196d"}},{"code_sha256_prefix":"21887b4a542f7643","entry":"create_video","repo":"mayuelala/followyourpose","repo_kind":"official","path":"inference_mmpose.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/inference_mmpose.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21887b4a542f7643"}},{"code_sha256_prefix":"639e9e02e5db3368","entry":"get_down_block","repo":"mayuelala/followyourpose","repo_kind":"official","path":"followyourpose/models/unet_blocks.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/followyourpose/models/unet_blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"639e9e02e5db3368"}},{"code_sha256_prefix":"b9a2d6517b8df4e4","entry":"get_frames","repo":"mayuelala/followyourpose","repo_kind":"official","path":"inference_mmpose.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/inference_mmpose.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9a2d6517b8df4e4"}},{"code_sha256_prefix":"4f31853cbd6d8701","entry":"get_mmpose_filter","repo":"mayuelala/followyourpose","repo_kind":"official","path":"inference_mmpose.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/inference_mmpose.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f31853cbd6d8701"}},{"code_sha256_prefix":"01feceecb56a7ffb","entry":"get_up_block","repo":"mayuelala/followyourpose","repo_kind":"official","path":"followyourpose/models/unet_blocks.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/followyourpose/models/unet_blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01feceecb56a7ffb"}},{"code_sha256_prefix":"a0a4d94af120c56f","entry":"init_prompt","repo":"mayuelala/followyourpose","repo_kind":"official","path":"followyourpose/util.py","file_url":"https://github.com/mayuelala/followyourpose/blob/HEAD/followyourpose/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0a4d94af120c56f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}