{"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/i2v-adapter-a-general-image-to-video-adapter","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","arxiv_id":"2312.16693","date":"2023-12-27","proceeding":null,"authors":["Xun Guo","Mingwu Zheng","Liang Hou","Yuan Gao","Yufan Deng","Pengfei Wan","Di Zhang","Yufan Liu","Weiming Hu","ZhengJun Zha","Haibin Huang","Chongyang Ma"],"abstract":"Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.","url_abs":"https://arxiv.org/abs/2312.16693v4","url_pdf":"https://arxiv.org/pdf/2312.16693v4.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":"i2v-adapter-a-general-image-to-video-adapter","repo_url":"https://github.com/KwaiVGI/I2V-Adapter","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"i2v-adapter-a-general-image-to-video-adapter","repo_url":"https://github.com/bytedance/x-dyna","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.16693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16693"}},"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/KwaiVGI/I2V-Adapter","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bytedance/x-dyna","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"ran":5,"unverified":20},"by_repo_kind":{"official":{"samples":17,"ran":8,"repositories":1},"listed":{"samples":12,"ran":1,"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":17,"samples":[{"code_sha256_prefix":"5105747c2711b1cb","entry":"FeedForward","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/models/ip_adapter.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/models/ip_adapter.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5105747c2711b1cb"}},{"code_sha256_prefix":"e285f4a541803f96","entry":"freq_mix_3d","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/freeinit_utils.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/freeinit_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e285f4a541803f96"}},{"code_sha256_prefix":"5753a1ae1b2b2a7a","entry":"gaussian_low_pass_filter","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/freeinit_utils.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/freeinit_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5753a1ae1b2b2a7a"}},{"code_sha256_prefix":"45f1cb4de58b3f3d","entry":"get_2d_sincos_pos_embed","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/embeddings.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/embeddings.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":"45f1cb4de58b3f3d"}},{"code_sha256_prefix":"924dfd50e7486609","entry":"get_freq_filter","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/freeinit_utils.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/freeinit_utils.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":"924dfd50e7486609"}},{"code_sha256_prefix":"e00393f9090e49e9","entry":"imread_resize","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/util.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/util.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":"e00393f9090e49e9"}},{"code_sha256_prefix":"d8bea9099f8a52b0","entry":"match_histogram","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/util.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/util.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":"d8bea9099f8a52b0"}},{"code_sha256_prefix":"2e3e408dc6b5d79d","entry":"resize_image","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/util.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e3e408dc6b5d79d"}},{"code_sha256_prefix":"4719c763c53be3fe","entry":"zero_module","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/models/motion_module.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/models/motion_module.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4719c763c53be3fe"}},{"code_sha256_prefix":"c8b7b26f11f30946","entry":"adjust_driving_video_to_src_image","repo":"bytedance/x-dyna","repo_kind":"listed","path":"inference_xdyna.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/inference_xdyna.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":"c8b7b26f11f30946"}},{"code_sha256_prefix":"4e1c711f8f37a1e7","entry":"convert_lora","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/convert_lora_safetensor_to_diffusers.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/convert_lora_safetensor_to_diffusers.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":"4e1c711f8f37a1e7"}},{"code_sha256_prefix":"ef399950f86ca4fc","entry":"convert_motion_lora_ckpt_to_diffusers","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/convert_lora_safetensor_to_diffusers.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/convert_lora_safetensor_to_diffusers.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":"ef399950f86ca4fc"}},{"code_sha256_prefix":"82ba71457fd0972f","entry":"extract_local_feature_from_single_img","repo":"bytedance/x-dyna","repo_kind":"listed","path":"inference_xdyna.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/inference_xdyna.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":"82ba71457fd0972f"}},{"code_sha256_prefix":"bf7f7ded00990ac3","entry":"find_best_frame_byheadpose_fa","repo":"bytedance/x-dyna","repo_kind":"listed","path":"inference_xdyna.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/inference_xdyna.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":"bf7f7ded00990ac3"}},{"code_sha256_prefix":"59fa7b38de05f443","entry":"get_2d_sincos_pos_embed_from_grid","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/embeddings.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/embeddings.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":"59fa7b38de05f443"}},{"code_sha256_prefix":"8b6c18061cbaa5fd","entry":"get_down_block","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/models/unet_blocks.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/models/unet_blocks.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":"8b6c18061cbaa5fd"}},{"code_sha256_prefix":"5f11ee52e92689bd","entry":"get_down_block","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/unet_blocks.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f11ee52e92689bd"}},{"code_sha256_prefix":"cd5f3777a951d27f","entry":"get_motion_module","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/motion_module.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/motion_module.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":"cd5f3777a951d27f"}},{"code_sha256_prefix":"38f69a3d1e46016d","entry":"get_timestep_embedding","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/embeddings.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/embeddings.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":"38f69a3d1e46016d"}},{"code_sha256_prefix":"07607267678d0f69","entry":"get_up_block","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/models/unet_blocks.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/models/unet_blocks.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":"07607267678d0f69"}},{"code_sha256_prefix":"c5952d08a7df1728","entry":"get_up_block","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/unet_blocks.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c5952d08a7df1728"}},{"code_sha256_prefix":"c9903af7cf272bc4","entry":"is_valid_image","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/image_processor.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/image_processor.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":"c9903af7cf272bc4"}},{"code_sha256_prefix":"53ccc214b8346dff","entry":"is_valid_image_imagelist","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/image_processor.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/image_processor.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":"53ccc214b8346dff"}},{"code_sha256_prefix":"230588e8f1237737","entry":"masked_mean","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/models/ip_adapter.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/models/ip_adapter.py","link_basis":"harvester_set","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":"230588e8f1237737"}},{"code_sha256_prefix":"dfb052a0af48540f","entry":"renew_resnet_paths","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/convert_from_ckpt.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/convert_from_ckpt.py","link_basis":"harvester_set","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":"dfb052a0af48540f"}},{"code_sha256_prefix":"c5ec9c13e456a046","entry":"renew_vae_resnet_paths","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/convert_from_ckpt.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/convert_from_ckpt.py","link_basis":"harvester_set","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":"c5ec9c13e456a046"}},{"code_sha256_prefix":"4cb2e2a2ca0bec9f","entry":"reshape_tensor","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/models/ip_adapter.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/models/ip_adapter.py","link_basis":"harvester_set","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":"4cb2e2a2ca0bec9f"}},{"code_sha256_prefix":"cea0bc82e0c96896","entry":"shave_segments","repo":"KwaiVGI/I2V-Adapter","repo_kind":"official","path":"src/utils/convert_from_ckpt.py","file_url":"https://github.com/KwaiVGI/I2V-Adapter/blob/HEAD/src/utils/convert_from_ckpt.py","link_basis":"harvester_set","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":"cea0bc82e0c96896"}},{"code_sha256_prefix":"da94debb8019ad46","entry":"zero_module","repo":"bytedance/x-dyna","repo_kind":"listed","path":"animatediff/models/controlnet.py","file_url":"https://github.com/bytedance/x-dyna/blob/HEAD/animatediff/models/controlnet.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":"da94debb8019ad46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}