跳过导航
🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video…
0:00 / 0:40

🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video…

Tencent HY

@TencentHunyuan3.5万 位关注者

在 X 上查看
640 个赞下载原帖

191,908 次观看

🚀 Introducing HunyuanCustom: An open-source, multimodal-driven architecture for customized video generation, powered by HunyuanVideo-13B. Outperforming existing open-source models, it rivals top closed-source solutions! 🎥 Highlights: ✅Subject Consistency: Maintains identity across single & multi-subject video generation. ✅Multimodal Inputs: Supports text, images, audio, and video for highly controlled outputs. ✅High-Quality Output: Industry-leading detail, motion smoothness, and lighting realism. Key Features: 1️⃣Single-Subject Video: Upload an image + text (e.g., “He’s walking a dog”) to create coherent videos with new actions, outfits, and scenes. 2️⃣Multi-Subject Video: Generate videos with multiple subjects (e.g., a man drinking coffee in a cozy room) from separate image inputs. 3️⃣Audio-Driven Video: Sync audio with visuals for talking or singing in any scene—perfect for digital avatars, virtual customer service, and more. 4️⃣Video-Driven Video: Seamlessly insert or replace subjects into any video for creative enhancements. Dive Deeper: 🌐Project: 📝Technical Details: 💻Code: The single-subject video capability is open-sourced and live on the Hunyuan website, with more features to be released soon! 👉 Try it now: #HunyuanCustom #VideoGeneration #AI #TencentHunyuan

10 条评论

评论来自 X (Twitter) 上的原帖

  • Hunyuan 的头像

    @TencentHunyuan

    Hugging Face

    44 个赞

  • Gold D. 的头像

    @EastInsiderW

    I wonder if one day we'll see Hunyuan 3D 2.5 open source? If so, when?

    6 个赞

  • Emily 的头像

    @IamEmily2050

    Congratulations on this achievement, and thank you for pushing open source forward. 🙏❤️

    3 个赞

  • Aaliya 的头像

    @aaliya_va

    This is seriously impressive! 🔥 Love the flexibility with multimodal inputs and the subject consistency

    2 个赞

  • Sentient Matrix 的头像

    @SentientMatrix

    😀 Looks highly promising! How much VRAM needed? Seems like it might run locally if based on 13B?

    2 个赞

  • rey 的头像

    @reyreyromonov

    @grok is this model uncensored or...?

    1 个赞

  • Amit 的头像

    @HeyAmit_

    Insane progress in video generation, will give it a try for sure.

  • Dhaval Makwana 的头像

    @heyDhavall

    This is cool! Let’s connect @TencentHunyuan

  • Sayak Paul 的头像

    @RisingSayak

    @aryanvs_ @_DhruvNair_

  • Amira Zairi 的头像

    @azed_ai

    Congrats Hunyuan team 🎉