Peihao Zhu

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To unleash the power of the foundation model, Seaweed-7B further enables a wide range of downstream applications including image-to-video generation, human video generation, subject-consistent video generation, video-audio joint generation, long video generation and storytelling, real-time generation, super-resolution generation, camera controlled generation. Check out our webpage and report for more details: Webpage: seaweed.video Paper: seaweed.video/seaweed.pdf It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.

@peter_wonka @BernardSGhanem @vcc_vis Many thanks🙌, @peter_wonka! I'm immensely grateful for your unwavering support during my PhD. Onward to new research horizons! #PhDPass🤣

Congratulations to @ZPdesu for passing his night time PhD defense! Thanks to the committee @BernardSGhanem Tobias Ritschel and Markus Hadwiger @vcc_vis.

Please reach out via email if you are interested in collaborations or our positions. We actively hire MS/PhD students, interns, remote interns, post-docs, and research scientists under generous conditions ideal for competitive research.

We have released the code for our MTG model. We have also released a Colab notebook to play around with your own images🙂 Code: github.com/ZPdesu/MindThe… Colab: colab.research.google.com/github/ZPdesu/…

Our paper on domain adaptation gets accepted at @iclr_conf #ICLR2022

Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks abs: arxiv.org/abs/2110.08398

Barbershop: GAN-based Image Compositing using Segmentation Masks pdf: arxiv.org/pdf/2106.01505… abs: arxiv.org/abs/2106.01505 project page: zpdesu.github.io/Barbershop/

StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows pdf: arxiv.org/pdf/2008.02401… abs: arxiv.org/abs/2008.02401 project page: rameenabdal.github.io/StyleFlow/

@ak92501 GitHub Page: zpdesu.github.io/SEAN/

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization pdf: arxiv.org/pdf/1911.12861… abs: arxiv.org/abs/1911.12861 video: youtube.com/watch?v=0Vbj9x…

GitHub Page: zpdesu.github.io/SEAN/ Code: github.com/ZPdesu/SEAN

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization youtu.be/0Vbj9xFgoUw via @YouTube