Multimodal AI for High-Fidelity Video Creation and Editing

Authors: (1) Dan Kondratyuk, Google Research and with Equal contribution; (2) Lijun Yu, Google Research, Carnegie Mellon University and with Equal contribution; (3) Xiuye Gu, Google Research and with Equal contribution; (4) Jose Lezama, Google Research and with Equal contribution; (5) Jonathan Huang, Google Research and with Equal contribution; (6) Grant Schindler, Google Research; (7) Rachel Hornung, Google Research; (8) Vighnesh Birodkar, Google Research; (9) Jimmy Yan, Google Research; (10) Krishna Somandepalli, Google Research; (11) Hassan Akbari, Google Research; (12) Yair Alon, Google Research; (13) Yong Cheng, Google DeepMind; (14) Josh Dillon, Google Research; (15) Agrim Gupta, Google Research; (16) Meera Hahn, Google Research; (17) Anja Hauth, Google Research; (18) David Hendon, Google Research; (19) Alonso Martinez, Google Research; (20) David Minnen, Google Research; (21) Mikhail Sirotenko, Google Research; (22) Kihyuk Sohn, Google Research; (23) Xuan Yang, Google Research; (24) Hartwig Adam, Google Research; (25) Ming-Hsuan Yang, Google Research; (26) Irfan Essa, Google Research; (27) Huisheng Wang, Google Research; (28) David A. Ross, Google Research; (29) Bryan Seybold, Google Research and with Equal contribution; (30) Lu Jiang, Google Research and with Equal contribution. Table of Links Abstract and 1 Introduction 2. Related Work 3. Model Overview and 3.1. Tokenization 3.2. Language Model Backbone and 3.3. Super-Resolution 4. LLM Pretraining for Generation 4.1. Task Prompt Design 4.2. Training Strategy 5. Experiments 5.1. Experimental Setup 5.2. Pretraining Task Analysis 5.3. Comparison with the State-of-the-Art 5.4. LLM’s Diverse Capabilities in Video Generation and 5.5. Limitations 6. Conclusion, Acknowledgements, and References A. Appendix 6. Conclusion VideoPoet demonstrates the potential of a large language model that is trained on discrete visual, text and audio tokens, in generating videos of compelling state-of-the-art quality. A particular strength of our model lies in its ability to generate high-fidelity, large, and complex motions. Our large language model formulation benefits from training across a variety of multimodal tasks with a unified architecture and vocabulary. Consequently, the pretrained model is adept at multi-task video creation, and serves as a foundation for a diverse variety of video generation related capabilities, including multiple forms of editing. Acknowledgements We give special thanks to Alex Siegman, Victor Gomes, and Brendan Jou for managing computing resources. We also give thanks to Aren Jansen, Marco Tagliasacchi, Neil Zeghidour, John Hershey for audio tokenization and processing, Angad Singh for storyboarding in “Rookie the Raccoon”, Cordelia Schmid for research discussions, David Salesin, Tomas Izo, and Rahul Sukthankar for their support, and Jay Yagnik for the initial concept. References Agostinelli, A., Denk, T. I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., Huang, Q., Jansen, A., Roberts, A., Tagliasacchi, M., et al. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325, 2023. Akbari, H., Kondratyuk, D., Cui, Y., Hornung, R., Wang, H., and Adam, H. Alternating gradient descent and mixture-of-experts for integrated multimodal perception. arXiv preprint arXiv:2305.06324, 2023. Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al. Palm 2 technical report. arXiv preprint arXiv:2305.10403, 2023. Bar-Tal, O., Chefer, H., Tov, O., Herrmann, C., Paiss, R., Zada, S., Ephrat, A., Hur, J., Li, Y., Michaeli, T., et al. Lumiere: A space-time diffusion model for video generation. arXiv preprint arXiv:2401.12945, 2024. Blattmann, A., Dockhorn, T., Kulal, S., Mendelevitch, D., Kilian, M., Lorenz, D., Levi, Y., English, Z., Voleti, V., Letts, A., et al. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127, 2023a. Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S. W., Fidler, S., and Kreis, K. Align your latents: High-resolution video synthesis with latent diffusion models. In CVPR, pp. 22563–22575, 2023b. Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258, 2021. Brooks, T., Holynski, A., and Efros, A. A. Instructpix2pix: Learning to follow image editing instructions. In CVPR, pp. 18392– 18402, 2023. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. Language models are few-shot learners. NeurIPS, 33: 1877–1901, 2020. Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., and Zisserman, A. A short note about kinetics-600. arXiv preprint arXiv:1808.01340, 2018. Ceylan, D., Huang, C.-H. P., and Mitra, N. J. Pix2video: Video editing using image diffusion. In CVPR, pp. 23206–23217, 2023. Chai, W., Guo, X., Wang, G., and Lu, Y. Stablevideo: Text-driven consistency-aware diffusion video editing. In CVPR, pp. 23040– 23050, 2023. Chang, H., Zhang, H., Jiang, L., Liu, C., and Freeman, W. T. Maskgit: Masked generative image transformer. In CVPR, pp. 11315–11325, 2022. Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K., Freeman, W. T., Rubinstein, M., et al. Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704, 2023. Chen, H., Xia, M., He, Y., Zhang, Y., Cun, X., Yang, S., Xing, J., Liu, Y., Chen, Q., Wang, X., et al. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512, 2023a. Chen, W., Wu, J., Xie, P., Wu, H., Li, J., Xia, X., Xiao, X., and Lin, L. Control-a-video: Controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840, 2023b. Chiu, M.-C., Chen, P.-Y., and Ma, X. Better may not be fairer: A study on subgroup discrepancy in image classification. In ICCV, pp. 4956–4966, 2023. Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. PaLM: Scaling language modeling with pathways. arXiv:2204.02311, 2022. Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., Lin, J., Zou, X., Shao, Z., Yang, H., et al. Cogview: Mastering text-to-image generation via transformers. NeurIPS, pp. 19822– 19835, 2021. Driess, D., Xia, F., Sajjadi, M. S., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T., et al. Palme: An embodied multimodal language model. arXiv preprint arXiv:2303.03378, 2023. Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., et al. GLaMs: Efficient scaling of language models with mixture-of-experts. In ICML, 2022. Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., et al. GLaMs: Efficient scaling of language models with mixture-of-experts. In ICML, 2022. Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., et al. GLaMs: Efficient scaling of language models with mixture-of-experts. In ICML, 2022. Esser, P., Rombach, R., and Ommer, B. Taming transformers for high-resolution image synthesis. In CVPR, pp. 12868–12878, 2020 EsserEsser, P., Chiu, J., Atighehchian, P., Granskog, J., and Germanidis, A. Structure and content-guided video synthesis with diffusion models. In CVPR, pp. 7346–7356, 2023.P., Chiu, J., Atighehchian, P., Granskog, J., and Germanidis, A. Structure and content-guided video syn Feng, R., Weng, W., Wang, Y., Yuan, Y., Bao, J., Luo, C., Chen, Z., and Guo, B. Ccedit: Creative and controllable video editing via diffusion models. arXiv preprint arXiv:2309.16496, 2023. Ge, S., Nah, S., Liu, G., Poon, T., Tao, A., Catanzaro, B., Jacobs, D., Huang, J.-B., Liu, M.-Y., and Balaji, Y. Preserve your own correlation: A noise prior for video diffusion models. In CVPR, pp. 22930–22941, 2023. Geyer, M., Bar-Tal, O., Bagon, S., and Dekel, T. Tokenflow: Consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373, 2023. Goyal, R., Ebrahimi Kahou, S., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. The “something something” video database for learning and evaluating visual common sense. In ICCV, 2017. Guo, Y., Yang, C., Rao, A., Wang, Y., Qiao, Y., Lin, D., and Dai, B. Animatediff: Animate your personalized text-toimage diffusion models without specific tuning. arXiv preprint arXiv:2307.04725, 2023. Gupta, A., Tian, S., Zhang, Y., Wu, J., Martın-Martın, R., and FeiFei, L. Maskvit: Masked visual pre-training for video prediction. arXiv preprint arXiv:2206.11894, 2022. He, Y., Yang, T., Zhang, Y., Shan, Y., and Chen, Q. Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221, 2(3):4, 2023. Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., Slaney, M., Weiss, R., and Wilson, K. Cnn architectures for large-scale audio classification. In ICASSP, 2017. URL https://arxiv.org/abs/1609.09430. Ho, J. and Salimans, T. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022. Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A., Kingma, D. P., Poole, B., Norouzi, M., Fleet, D. J., et al. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303, 2022a. Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., and Fleet, D. J. Video diffusion models. arXiv:2204.03458, 2022b. Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. d. L., Hendricks, L. A., Welbl, J., Clark, A., et al. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556, 2022. Hong, W., Ding, M., Zheng, W., Liu, X., and Tang, J. Cogvideo: Large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868, 2022. Hu, A., Russell, L., Yeo, H., Murez, Z., Fedoseev, G., Kendall, A., Shotton, J., and Corrado, G. Gaia-1: A generative world model for autonomous driving. arXiv preprint arXiv:2309.17080, 2023. Li, R., Allal, L. B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J., et al. StarCoder: may the source be with you! arXiv:2305.06161, 2023. Liew, J. H., Yan, H., Zhang, J., Xu, Z., and Feng, J. Magicedit: High-fidelity and temporally coherent video editing. arXiv preprint arXiv:2308.14749, 2023. Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., and Ermon, S. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073, 2021. Nash, C., Carreira, J., Walker, J., Barr, I., Jaegle, A., Malinowski, M., and Battaglia, P. Transframer: Arbitrary frame prediction with generative models. arXiv preprint arXiv:2203.09494, 2022. OpenAI. GPT-4 technical report. arXiv:2303.08774, 2023. Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., and Sorkine-Hornung, A. A benchmark dataset and evaluation methodology for video object segmentation. In CVPR, 2016. Pika. Pika 1.0, 2023. URL https://pika.art/launch. Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Muller, J., Penna, J., and Rombach, R. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952, 2023. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., and Liu, P. J. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(1):5485–5551, 2020. Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., and Sutskever, I. Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092, 2021. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2):3, 2022. Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., and Koltun, V. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE TPAMI, 44(3):1623– 1637, 2020. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. High-resolution image synthesis with latent diffusion models. In CVPR, pp. 10684–10695, 2022. Rubenstein, P. K., Asawaroengchai, C., Nguyen, D. D., Bapna, A., Borsos, Z., Quitry, F. d. C., Chen, P., Badawy, D. E., Han, W., Kharitonov, E., et al. Audiopalm: A large language model that can speak and listen. arXiv preprint arXiv:2306.12925, 2023. Runway. Gen2, 2023. URL https://runwayml.com/. Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al. Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS, 35:36479–36494, 2022. Saito, M., Saito, S., Koyama, M., and Kobayashi, S. Train sparsely, generate densely: Memory-efficient unsupervised training of high-resolution temporal gan. IJCV, 128(10):2586–2606, 2020. Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, 35:25278–25294, 2022. Schumann, C., Ricco, S., Prabhu, U., Ferrari, V., and Pantofaru, C. A step toward more inclusive people annotations for fairness. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp. 916–925, 2021. Schumann, C., Olanubi, G. O., Wright, A., Monk, E., Heldreth, C., and Ricco, S. Consensus and subjectivity of skin tone annotation for ML fairness. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023. URL https://openreview.net/forum? id=L9I9FhHfS3. Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., et al. Make-a-video: Textto-video generation without text-video data. arXiv preprint arXiv:2209.14792, 2022. Soomro, K., Zamir, A. R., and Shah, M. Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402, 2012. Sun, D., Herrmann, C., Reda, F., Rubinstein, M., Fleet, D. J., and Freeman, W. T. Disentangling architecture and training for optical flow. In ECCV, 2022. Tang, Z., Yang, Z., Zhu, C., Zeng, M., and Bansal, M. Anyto-any generation via composable diffusion. arXiv preprint arXiv:2305.11846, 2023. Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., and Li, Y. Maxvit: Multi-axis vision transformer. In ECCV, pp. 459–479, 2022. Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., and Gelly, S. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717, 2018. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. Attention is all you need. NeurIPS, 30, 2017. Villegas, R., Babaeizadeh, M., Kindermans, P.-J., Moraldo, H., Zhang, H., Saffar, M. T., Castro, S., Kunze, J., and Erhan, D. Phenaki: Variable length video generation from open domain textual description. arXiv preprint arXiv:2210.02399, 2022. Voleti, V., Jolicoeur-Martineau, A., and Pal, C. Mcvd-masked conditional video diffusion for prediction, generation, and interpolation. NeurIPS, 35:23371–23385, 2022. Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., and Zhang, S. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571, 2023a. Wang, W., Xie, K., Liu, Z., Chen, H., Cao, Y., Wang, X., and Shen, C. Zero-shot video editing using off-the-shelf image diffusion models. arXiv preprint arXiv:2303.17599, 2023b. Wang, W., Yang, H., Tuo, Z., He, H., Zhu, J., Fu, J., and Liu, J. Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation. arXiv preprint arXiv:2305.10874, 2023c. Wang, Y., He, Y., Li, Y., Li, K., Yu, J., Ma, X., Chen, X., Wang, Y., Luo, P., Liu, Z., et al. Internvid: A large-scale video-text dataset for multimodal understanding and generation. arXiv preprint arXiv:2307.06942, 2023d. Wu, C., Huang, L., Zhang, Q., Li, B., Ji, L., Yang, F., Sapiro, G., and Duan, N. Godiva: Generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806, 2021. Xu, J., Mei, T., Yao, T., and Rui, Y. Msr-vtt: A large video description dataset for bridging video and language. In CVPR, pp. 5288–5296, 2016. Yan, W., Zhang, Y., Abbeel, P., and Srinivas, A. Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157, 2021. Yu, J., Xu, Y., Koh, J. Y., Luong, T., Baid, G., Wang, Z., Vasudevan, V., Ku, A., Yang, Y., Ayan, B. K., et al. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, 2022. Yu, L., Cheng, Y., Sohn, K., Lezama, J., Zhang, H., Chang, H., Hauptmann, A. G., Yang, M.-H., Hao, Y., Essa, I., et al. Magvit: Masked generative video transformer. In CVPR, pp. 10459– 10469, 2023a. Yu, L., Cheng, Y., Wang, Z., Kumar, V., Macherey, W., Huang, Y., Ross, D. A., Essa, I., Bisk, Y., Yang, M.-H., et al. Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms. arXiv preprint arXiv:2306.17842, 2023b. Yu, L., Lezama, J., Gundavarapu, N. B., Versari, L., Sohn, K., Minnen, D., Cheng, Y., Gupta, A., Gu, X., Hauptmann, A. G., et al. Language model beats diffusion–tokenizer is key to visual generation. arXiv preprint arXiv:2310.05737, 2023c. Yu, S., Sohn, K., Kim, S., and Shin, J. Video probabilistic diffusion models in projected latent space. In CVPR, pp. 18456–18466, 2023d. Zeghidour, N., Luebs, A., Omran, A., Skoglund, J., and Tagliasacchi, M. Soundstream: An end-to-end neural audio codec. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30:495–507, 2021. Zeng, Y., Wei, G., Zheng, J., Zou, J., Wei, Y., Zhang, Y., and Li, H. Make pixels dance: High-dynamic video generation. arXiv preprint arXiv:2311.10982, 2023. Zhang, D. J., Wu, J. Z., Liu, J.-W., Zhao, R., Ran, L., Gu, Y., Gao, D., and Shou, M. Z. Show-1: Marrying pixel and latent diffusion models for text-to-video generation. arXiv preprint arXiv:2309.15818, 2023a. Zhang, L., Rao, A., and Agrawala, M. Adding conditional control to text-to-image diffusion models. In CVPR, pp. 3836–3847, 2023b. Zhang, Y., Jiang, L., Turk, G., and Yang, D. Auditing gender presentation differences in text-to-image models. arXiv preprint arXiv:2302.03675, 2023c. Zhou, C., Liu, P., Xu, P., Iyer, S., Sun, J., Mao, Y., Ma, X., Efrat, A., Yu, P., Yu, L., et al. Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206, 2023. Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., and Feng, J. Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018, 2022. Zitkovich, B., Yu, T., Xu, S., Xu, P., Xiao, T., Xia, F., Wu, J., Wohlhart, P., Welker, S., Wahid, A., et al. RT-2: Vision-language-action models transfer web knowledge to robotic control. In CoRL, 2023. This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Dan Kondratyuk, Google Research and with Equal contribution; (2) Lijun Yu, Google Research, Carnegie Mellon University and with Equal contribution; (3) Xiuye Gu, Google Research and with Equal contribution; (4) Jose Lezama, Google Research and with Equal contribution; (5) Jonathan Huang, Google Research and with Equal contribution; (6) Grant Schindler, Google Research; (7) Rachel Hornung, Google Research; (8) Vighnesh Birodkar, Google Research; (9) Jimmy Yan, Google Research; (10) Krishna Somandepalli, Google Research; (11) Hassan Akbari, Google Research; (12) Yair Alon, Google Research; (13) Yong Cheng, Google DeepMind; (14) Josh Dillon, Google Research; (15) Agrim Gupta, Google Research; (16) Meera Hahn, Google Research; (17) Anja Hauth, Google Research; (18) David Hendon, Google Research; (19) Alonso Martinez, Google Research; (20) David Minnen, Google Research; (21) Mikhail Sirotenko, Google Research; (22) Kihyuk Sohn, Google Research; (23) Xuan Yang, Google Research; (24) Hartwig Adam, Google Research; (25) Ming-Hsuan Yang, Google Research; (26) Irfan Essa, Google Research; (27) Huisheng Wang, Google Research; (28) David A. Ross, Google Research; (29) Bryan Seybold, Google Research and with Equal contribution; (30) Lu Jiang, Google Research and with Equal contribution. Authors: Authors: (1) Dan Kondratyuk, Google Research and with Equal contribution; (2) Lijun Yu, Google Research, Carnegie Mellon University and with Equal contribution; (3) Xiuye Gu, Google Research and with Equal contribution; (4) Jose Lezama, Google Research and with Equal contribution; (5) Jonathan Huang, Google Research and with Equal contribution; (6) Grant Schindler, Google Research; (7) Rachel Hornung, Google Research; (8) Vighnesh Birodkar, Google Research; (9) Jimmy Yan, Google Research; (10) Krishna Somandepalli, Google Research; (11) Hassan Akbari, Google Research; (12) Yair Alon, Google Research; (13) Yong Cheng, Google DeepMind; (14) Josh Dillon, Google Research; (15) Agrim Gupta, Google Research; (16) Meera Hahn, Google Research; (17) Anja Hauth, Google Research; (18) David Hendon, Google Research; (19) Alonso Martinez, Google Research; (20) David Minnen, Google Research; (21) Mikhail Sirotenko, Google Research; (22) Kihyuk Sohn, Google Research; (23) Xuan Yang, Google Research; (24) Hartwig Adam, Google Research; (25) Ming-Hsuan Yang, Google Research; (26) Irfan Essa, Google Research; (27) Huisheng Wang, Google Research; (28) David A. Ross, Google Research; (29) Bryan Seybold, Google Research and with Equal contribution; (30) Lu Jiang, Google Research and with Equal contribution. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2. Related Work 2. Related Work 3. Model Overview and 3.1. Tokenization 3. Model Overview and 3.1. Tokenization 3.2. Language Model Backbone and 3.3. Super-Resolution 3.2. Language Model Backbone and 3.3. Super-Resolution 4. LLM Pretraining for Generation 4.1. Task Prompt Design 4.1. Task Prompt Design 4.2. Training Strategy 4.2. Training Strategy 5. Experiments 5.1. Experimental Setup 5.1. Experimental Setup 5.2. Pretraining Task Analysis 5.2. Pretraining Task Analysis 5.3. Comparison with the State-of-the-Art 5.3. Comparison with the State-of-the-Art 5.4. LLM’s Diverse Capabilities in Video Generation and 5.5. Limitations 5.4. LLM’s Diverse Capabilities in Video Generation and 5.5. Limitations 6. Conclusion, Acknowledgements, and References 6. Conclusion, Acknowledgements, and References A. Appendix A. Appendix 6. Conclusion VideoPoet demonstrates the potential of a large language model that is trained on discrete visual, text and audio tokens, in generating videos of compelling state-of-the-art quality. A particular strength of our model lies in its ability to generate high-fidelity, large, and complex motions. Our large language model formulation benefits from training across a variety of multimodal tasks with a unified architecture and vocabulary. Consequently, the pretrained model is adept at multi-task video creation, and serves as a foundation for a diverse variety of video generation related capabilities, including multiple forms of editing. Acknowledgements We give special thanks to Alex Siegman, Victor Gomes, and Brendan Jou for managing computing resources. We also give thanks to Aren Jansen, Marco Tagliasacchi, Neil Zeghidour, John Hershey for audio tokenization and processing, Angad Singh for storyboarding in “Rookie the Raccoon”, Cordelia Schmid for research discussions, David Salesin, Tomas Izo, and Rahul Sukthankar for their support, and Jay Yagnik for the initial concept. References Agostinelli, A., Denk, T. I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., Huang, Q., Jansen, A., Roberts, A., Tagliasacchi, M., et al. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325, 2023. Akbari, H., Kondratyuk, D., Cui, Y., Hornung, R., Wang, H., and Adam, H. Alternating gradient descent and mixture-of-experts for integrated multimodal perception. arXiv preprint arXiv:2305.06324, 2023. Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al. Palm 2 technical report. arXiv preprint arXiv:2305.10403, 2023. Bar-Tal, O., Chefer, H., Tov, O., Herrmann, C., Paiss, R., Zada, S., Ephrat, A., Hur, J., Li, Y., Michaeli, T., et al. Lumiere: A space-time diffusion model for video generation. arXiv preprint arXiv:2401.12945, 2024. Blattmann, A., Dockhorn, T., Kulal, S., Mendelevitch, D., Kilian, M., Lorenz, D., Levi, Y., English, Z., Voleti, V., Letts, A., et al. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127, 2023a. Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S. W., Fidler, S., and Kreis, K. Align your latents: High-resolution video synthesis with latent diffusion models. In CVPR, pp. 22563–22575, 2023b. B ommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258, 2021. B Brooks, T., Holynski, A., and Efros, A. A. Instructpix2pix: Learning to follow image editing instructions. In CVPR, pp. 18392– 18402, 2023. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. Language models are few-shot learners. NeurIPS, 33: 1877–1901, 2020. Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., and Zisserman, A. A short note about kinetics-600. arXiv preprint arXiv:1808.01340, 2018. Ceylan, D., Huang, C.-H. P., and Mitra, N. J. Pix2video: Video editing using image diffusion. In CVPR, pp. 23206–23217, 2023. Chai, W., Guo, X., Wang, G., and Lu, Y. Stablevideo: Text-driven consistency-aware diffusion video editing. In CVPR, pp. 23040– 23050, 2023. Chang, H., Zhang, H., Jiang, L., Liu, C., and Freeman, W. T. Maskgit: Masked generative image transformer. In CVPR, pp. 11315–11325, 2022. Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K., Freeman, W. T., Rubinstein, M., et al. Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704, 2023. Chen, H., Xia, M., He, Y., Zhang, Y., Cun, X., Yang, S., Xing, J., Liu, Y., Chen, Q., Wang, X., et al. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512, 2023a. Chen, W., Wu, J., Xie, P., Wu, H., Li, J., Xia, X., Xiao, X., and Lin, L. Control-a-video: Controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840, 2023b. Chiu, M.-C., Chen, P.-Y., and Ma, X. Better may not be fairer: A study on subgroup discrepancy in image classification. In ICCV, pp. 4956–4966, 2023. Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. PaLM: Scaling language modeling with pathways. arXiv:2204.02311, 2022. Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., Lin, J., Zou, X., Shao, Z., Yang, H., et al. Cogview: Mastering text-to-image generation via transformers. NeurIPS, pp. 19822– 19835, 2021. Driess, D., Xia, F., Sajjadi, M. S., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T., et al. Palme: An embodied multimodal language model. arXiv preprint arXiv:2303.03378, 2023. Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., et al. GLaMs: Efficient scaling of language models with mixture-of-experts. In ICML, 2022. Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., et al. GLaMs: Efficient scaling of language models with mixture-of-experts. In ICML, 2022. Du, N., Huang, Y., Dai, A. M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A. W., Firat, O., et al. GLaMs: Efficient scaling of language models with mixture-of-experts. In ICML, 2022. Esser, P., Rombach, R., and Ommer, B. Taming transformers for high-resolution image synthesis. In CVPR, pp. 12868–12878, 2020 EsserEsser, P., Chiu, J., Atighehchian, P., Granskog, J., and Germanidis, A. Structure and content-guided video synthesis with diffusion models. In CVPR, pp. 7346–7356, 2023.P., Chiu, J., Atighehchian, P., Granskog, J., and Germanidis, A. Structure and content-guided video syn Feng, R., Weng, W., Wang, Y., Yuan, Y., Bao, J., Luo, C., Chen, Z., and Guo, B. Ccedit: Creative and controllable video editing via diffusion models. arXiv preprint arXiv:2309.16496, 2023. Ge, S., Nah, S., Liu, G., Poon, T., Tao, A., Catanzaro, B., Jacobs, D., Huang, J.-B., Liu, M.-Y., and Balaji, Y. Preserve your own correlation: A noise prior for video diffusion models. In CVPR, pp. 22930–22941, 2023. Geyer, M., Bar-Tal, O., Bagon, S., and Dekel, T. Tokenflow: Consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373, 2023. Goyal, R., Ebrahimi Kahou, S., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. The “something something” video database for learning and evaluating visual common sense. In ICCV, 2017. Guo, Y., Yang, C., Rao, A., Wang, Y., Qiao, Y., Lin, D., and Dai, B. Animatediff: Animate your personalized text-toimage diffusion models without specific tuning. arXiv preprint arXiv:2307.04725, 2023. Gupta, A., Tian, S., Zhang, Y., Wu, J., Martın-Martın, R., and FeiFei, L. Maskvit: Masked visual pre-training for video prediction. arXiv preprint arXiv:2206.11894, 2022. He, Y., Yang, T., Zhang, Y., Shan, Y., and Chen, Q. Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221, 2(3):4, 2023. Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., Slaney, M., Weiss, R., and Wilson, K. Cnn architectures for large-scale audio classification. In ICASSP, 2017. URL https://arxiv.org/abs/1609.09430. Ho, J. and Salimans, T. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598, 2022. Ho, J., Chan, W., Saharia, C., Whang, J., Gao, R., Gritsenko, A., Kingma, D. P., Poole, B., Norouzi, M., Fleet, D. J., et al. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303, 2022a. Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., and Fleet, D. J. Video diffusion models. arXiv:2204.03458, 2022b. Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. d. L., Hendricks, L. A., Welbl, J., Clark, A., et al. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556, 2022. Hong, W., Ding, M., Zheng, W., Liu, X., and Tang, J. Cogvideo: Large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868, 2022. Hu, A., Russell, L., Yeo, H., Murez, Z., Fedoseev, G., Kendall, A., Shotton, J., and Corrado, G. Gaia-1: A generative world model for autonomous driving. arXiv preprint arXiv:2309.17080, 2023. Li, R., Allal, L. B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J., et al. StarCoder: may the source be with you! arXiv:2305.06161, 2023. Liew, J. H., Yan, H., Zhang, J., Xu, Z., and Feng, J. Magicedit: High-fidelity and temporally coherent video editing. arXiv preprint arXiv:2308.14749, 2023. Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., and Ermon, S. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073, 2021. Nash, C., Carreira, J., Walker, J., Barr, I., Jaegle, A., Malinowski, M., and Battaglia, P. Transframer: Arbitrary frame prediction with generative models. arXiv preprint arXiv:2203.09494, 2022. OpenAI. GPT-4 technical report. arXiv:2303.08774, 2023. Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., and Sorkine-Hornung, A. A benchmark dataset and evaluation methodology for video object segmentation. In CVPR, 2016. Pika. Pika 1.0, 2023. URL https://pika.art/launch. Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., Muller, J., Penna, J., and Rombach, R. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952, 2023. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., and Liu, P. J. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(1):5485–5551, 2020. Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., and Sutskever, I. Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092, 2021. Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2):3, 2022. Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., and Koltun, V. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE TPAMI, 44(3):1623– 1637, 2020. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. High-resolution image synthesis with latent diffusion models. In CVPR, pp. 10684–10695, 2022. Rubenstein, P. K., Asawaroengchai, C., Nguyen, D. D., Bapna, A., Borsos, Z., Quitry, F. d. C., Chen, P., Badawy, D. E., Han, W., Kharitonov, E., et al. Audiopalm: A large language model that can speak and listen. arXiv preprint arXiv:2306.12925, 2023. Runway. Gen2, 2023. URL https://runwayml.com/. Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al. Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS, 35:36479–36494, 2022. Saito, M., Saito, S., Koyama, M., and Kobayashi, S. Train sparsely, generate densely: Memory-efficient unsupervised training of high-resolution temporal gan. IJCV, 128(10):2586–2606, 2020. Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, 35:25278–25294, 2022. Schumann, C., Ricco, S., Prabhu, U., Ferrari, V., and Pantofaru, C. A step toward more inclusive people annotations for fairness. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp. 916–925, 2021. Schumann, C., Olanubi, G. O., Wright, A., Monk, E., Heldreth, C., and Ricco, S. Consensus and subjectivity of skin tone annotation for ML fairness. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2023. URL https://openreview.net/forum? id=L9I9FhHfS3. Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O., et al. Make-a-video: Textto-video generation without text-video data. arXiv preprint arXiv:2209.14792, 2022. Soomro, K., Zamir, A. R., and Shah, M. Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402, 2012. Sun, D., Herrmann, C., Reda, F., Rubinstein, M., Fleet, D. J., and Freeman, W. T. Disentangling architecture and training for optical flow. In ECCV, 2022. Tang, Z., Yang, Z., Zhu, C., Zeng, M., and Bansal, M. Anyto-any generation via composable diffusion. arXiv preprint arXiv:2305.11846, 2023. Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., and Li, Y. Maxvit: Multi-axis vision transformer. In ECCV, pp. 459–479, 2022. Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., and Gelly, S. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717, 2018. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. Attention is all you need. NeurIPS, 30, 2017. Villegas, R., Babaeizadeh, M., Kindermans, P.-J., Moraldo, H., Zhang, H., Saffar, M. T., Castro, S., Kunze, J., and Erhan, D. Phenaki: Variable length video generation from open domain textual description. arXiv preprint arXiv:2210.02399, 2022. Voleti, V., Jolicoeur-Martineau, A., and Pal, C. Mcvd-masked conditional video diffusion for prediction, generation, and interpolation. NeurIPS, 35:23371–23385, 2022. Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., and Zhang, S. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571, 2023a. Wang, W., Xie, K., Liu, Z., Chen, H., Cao, Y., Wang, X., and Shen, C. Zero-shot video editing using off-the-shelf image diffusion models. arXiv preprint arXiv:2303.17599, 2023b. Wang, W., Yang, H., Tuo, Z., He, H., Zhu, J., Fu, J., and Liu, J. Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation. arXiv preprint arXiv:2305.10874, 2023c. Wang, Y., He, Y., Li, Y., Li, K., Yu, J., Ma, X., Chen, X., Wang, Y., Luo, P., Liu, Z., et al. Internvid: A large-scale video-text dataset for multimodal understanding and generation. arXiv preprint arXiv:2307.06942, 2023d. Wu, C., Huang, L., Zhang, Q., Li, B., Ji, L., Yang, F., Sapiro, G., and Duan, N. Godiva: Generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806, 2021. Xu, J., Mei, T., Yao, T., and Rui, Y. Msr-vtt: A large video description dataset for bridging video and language. In CVPR, pp. 5288–5296, 2016. Yan, W., Zhang, Y., Abbeel, P., and Srinivas, A. Videogpt: Video generation using vq-vae and transformers. arXiv preprint arXiv:2104.10157, 2021. Yu, J., Xu, Y., Koh, J. Y., Luong, T., Baid, G., Wang, Z., Vasudevan, V., Ku, A., Yang, Y., Ayan, B. K., et al. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, 2022. Yu, L., Cheng, Y., Sohn, K., Lezama, J., Zhang, H., Chang, H., Hauptmann, A. G., Yang, M.-H., Hao, Y., Essa, I., et al. Magvit: Masked generative video transformer. In CVPR, pp. 10459– 10469, 2023a. Yu, L., Cheng, Y., Wang, Z., Kumar, V., Macherey, W., Huang, Y., Ross, D. A., Essa, I., Bisk, Y., Yang, M.-H., et al. Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms. arXiv preprint arXiv:2306.17842, 2023b. Yu, L., Lezama, J., Gundavarapu, N. B., Versari, L., Sohn, K., Minnen, D., Cheng, Y., Gupta, A., Gu, X., Hauptmann, A. G., et al. Language model beats diffusion–tokenizer is key to visual generation. arXiv preprint arXiv:2310.05737, 2023c. Yu, S., Sohn, K., Kim, S., and Shin, J. Video probabilistic diffusion models in projected latent space. In CVPR, pp. 18456–18466, 2023d. Zeghidour, N., Luebs, A., Omran, A., Skoglund, J., and Tagliasacchi, M. Soundstream: An end-to-end neural audio codec. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30:495–507, 2021. Zeng, Y., Wei, G., Zheng, J., Zou, J., Wei, Y., Zhang, Y., and Li, H. Make pixels dance: High-dynamic video generation. arXiv preprint arXiv:2311.10982, 2023. Zhang, D. J., Wu, J. Z., Liu, J.-W., Zhao, R., Ran, L., Gu, Y., Gao, D., and Shou, M. Z. Show-1: Marrying pixel and latent diffusion models for text-to-video generation. arXiv preprint arXiv:2309.15818, 2023a. Zhang, L., Rao, A., and Agrawala, M. Adding conditional control to text-to-image diffusion models. In CVPR, pp. 3836–3847, 2023b. Zhang, Y., Jiang, L., Turk, G., and Yang, D. Auditing gender presentation differences in text-to-image models. arXiv preprint arXiv:2302.03675, 2023c. Zhou, C., Liu, P., Xu, P., Iyer, S., Sun, J., Mao, Y., Ma, X., Efrat, A., Yu, P., Yu, L., et al. Lima: Less is more for alignment. arXiv preprint arXiv:2305.11206, 2023. Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., and Feng, J. Magicvideo: Efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018, 2022. Zitkovich, B., Yu, T., Xu, S., Xu, P., Xiao, T., Xia, F., Wu, J., Wohlhart, P., Welker, S., Wahid, A., et al. RT-2: Vision-language-action models transfer web knowledge to robotic control. In CoRL, 2023. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv