🪛 AgileAvatar: HQ stylized 3D #Avatar 🪛

👉#ByteDance unveils a novel self-supervised framework for #3D avatars

😎Review https://bit.ly/3kaOAw6
😎Project ssangx.github.io/projects/agileavatar
😎Paper ssangx.github.io/pubs/2022-SIGGRAPHAsia-AgileAvatar.pdf

🍥 PanoHead: 3D Full-Head Synthesis 🍥

👉#ByteDance (+UW-M) unveils PanoHead: 360◦ view-consistent portraits from a single-view image

😎Review https://t.ly/MrLNR
😎Paper arxiv.org/pdf/2303.13071.pdf
😎Project sizhean.github.io/panohead
😎Code github.com/sizhean/panohead

🐤 MagicVideo-V2 announced! 🐤

👉#Bytedance announces a novel multi-stage pipeline capable of generating high-aesthetic videos from textual description

👉Review https://t.ly/zIq4v
👉Project https://lnkd.in/dKUrJPJd
👉Paper https://lnkd.in/dixnN-kU

🆔 Magic-Me: ID-Specific Video 🆔

👉#ByteDance VCD: with just a few images of a specific identity it can generate temporal consistent videos aligned with the given prompt

👉Review https://t.ly/qjJ2O
👉Paper arxiv.org/pdf/2402.09368.pdf
👉Project magic-me-webpage.github.io
👉Code github.com/Zhen-Dong/Magic-Me

⛽ VoRA: Vision as LoRA ⛽

👉#ByteDance unveils Vision as LoRA (VoRA), a novel paradigm converting LLMs into Multimodal Large Language Models (MLLMs) by integrating vision-specific LoRA layers. All training data, codes, and model weights available💙

👉Review https://t.ly/guNVN
👉Paper arxiv.org/pdf/2503.20680
👉Repo github.com/Hon-Wong/VoRA
👉Project georgeluimmortal.github.io/vora-homepage.github.io/

🥶 OmniHuman-1.5 🥶

👉#ByteDance proposes a novel framework designed to generate character animations that are not only physically plausible but also semantically coherent and expressive. Coherency with speech's rhythm, prosody and semantic content. Impressive results but no code 🥺

👉Review https://t.ly/CnRmX
👉Paper arxiv.org/pdf/2508.19209
👉Project omnihuman-lab.github.io/v1_5/
👉Repo 🥺

🐙Human-Centric Video Generation🐙

👉Tsinghua & #ByteDance unveil HuMo: a unified, human-centric video generation framework designed to produce HQ fine-grained, and controllable human videos from multimodal inputs: text prompt following, consistent subject preservation, synchronized audio-driven motion. Repo released under Apache2.0💙

👉Review https://t.ly/3S8Yb
👉Paper https://arxiv.org/pdf/2509.08519
👉Project https://phantom-video.github.io/HuMo/
👉Repo https://github.com/Phantom-video/HuMo