sekotalk

[sekotalk @seko_talk]

🌈No VE/VAE! SenseNova U1,native multimodal unified model is OPEN SOURCE!
👾1-click long text to infographics & interleaved text-image reasoning.
https://t.co/6FpFoshlDX
🤖 Fun Skills inside: Poster replication, resume gen & more!
https://t.co/AaAeTcwnCY
🌟Star us if you like it!

[Lei Yang @drowsyleilei]

🤯Amazed by Image-2/NB 2, we kept asking: what’s the path behind them? We see native unified multimodal models as promising.
🚀Today, we open-source SenseNova U1, with solid und. & gen.(esp. Infographic & Interleaved). Hope to improve with the community toward Agentic Learning.🤝

[Lei Yang @drowsyleilei]

🤯Amazed by Image-2/NB 2, we kept asking: what’s the path behind them? We see native unified multimodal models as promising.
🚀Today, we open-source SenseNova U1, with solid und. & gen.(esp. Infographic & Interleaved). Hope to improve with the community toward Agentic Learning.🤝

[sekotalk @seko_talk]

@dlp3d_ai @elonmusk Wow! Awesome Work!🤩

[sekotalk @seko_talk]

📺 Check out this 3-minute video podcast for a quick overview of #PhasedDMD, an improved distillation technique for few-step image and video generation models like #qwenimage and #wan22 !

🔗 https://t.co/gIBbnQhdgt

Brought to you by SekoTalk👥 & Bytedance Podcast TTS 🎙️

[sekotalk @seko_talk]

SekoTalk creates a MV🎤based on a character and the music produced by @minimax_ai @Hailuo_AI 's latest Music 1.5
🤩Watch the full 3.5-min performance👇
Try it yourself (✨limited free✨)👉 https://t.co/RZoikwB8DN or https://t.co/mKBAXhiQCd
Explore more👉https://t.co/VDQldMmrlc

[sekotalk @seko_talk]

🚀 Excited to share SekoTalk: an audio-driven digital human generation model!
🌟 Teamed with LightX2V, SekoTalk generates lifelike characters in just 4 NFEs.
🆓 Try it free!
SekoTalk: https://t.co/RZoikwB8DN (More demos: https://t.co/VDQldMmrlc)
LightX2V: https://t.co/mKBAXhiQCd