#flux3 — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #flux3, aggregated by home.social.
-
أطلقت الشركة الناشئة الألمانية Black Forest Labs نموذج الذكاء الاصطناعي Flux 3، وهو أول نموذج متعدد الوسائط ينشئ مقاطع فيديو تصل مدتها إلى 20 ثانية مصحوبة بصوت متزامن. يدعم النظام تحويل النص والصورة إلى فيديو، إضافة إلى إنشاء حوارات بلغات متعددة وتعبيرات وجه طبيعية. كما أظهرت النتائج الداخلية تفوق النموذج بنسبة كبيرة على منافسين مثل Runway Gen 4.5 وLuma Ray 3.2. يتوفر Flux 3 Video حالياً، مع خطط لإطلاق نسخة مفتوحة.
-
أطلقت الشركة الناشئة الألمانية Black Forest Labs نموذج الذكاء الاصطناعي Flux 3، وهو أول نموذج متعدد الوسائط ينشئ مقاطع فيديو تصل مدتها إلى 20 ثانية مصحوبة بصوت متزامن. يدعم النظام تحويل النص والصورة إلى فيديو، إضافة إلى إنشاء حوارات بلغات متعددة وتعبيرات وجه طبيعية. كما أظهرت النتائج الداخلية تفوق النموذج بنسبة كبيرة على منافسين مثل Runway Gen 4.5 وLuma Ray 3.2. يتوفر Flux 3 Video حالياً، مع خطط لإطلاق نسخة مفتوحة.
-
Flux 3 X Mimic: The Next Generation of Video-Action Models
https://bfl.ai/blog/flux-3-mimic
Comments: https://news.ycombinator.com/item?id=49033127
#HackerNews #Flux3 #Mimic #VideoAction #Models #NextGen #AI #Technology
-
Flux 3 X Mimic: The Next Generation of Video-Action Models
https://bfl.ai/blog/flux-3-mimic
Comments: https://news.ycombinator.com/item?id=49033127
#HackerNews #Flux3 #Mimic #VideoAction #Models #NextGen #AI #Technology
-
🚀 Welcome to FLUX 3, where we mash together images, videos, and sounds into one big #AI smoothie, because why not? 🎨🤖 Don't worry if you don't understand what "multimodal flow models" mean—neither does anyone else, but it sounds impressive in meetings! 💼👓
https://bfl.ai/blog/flux-3 #FLUX3 #multimodal #creativity #technology #innovation #HackerNews #ngated -
🚀 Welcome to FLUX 3, where we mash together images, videos, and sounds into one big #AI smoothie, because why not? 🎨🤖 Don't worry if you don't understand what "multimodal flow models" mean—neither does anyone else, but it sounds impressive in meetings! 💼👓
https://bfl.ai/blog/flux-3 #FLUX3 #multimodal #creativity #technology #innovation #HackerNews #ngated -
🚀 Welcome to FLUX 3, where we mash together images, videos, and sounds into one big #AI smoothie, because why not? 🎨🤖 Don't worry if you don't understand what "multimodal flow models" mean—neither does anyone else, but it sounds impressive in meetings! 💼👓
https://bfl.ai/blog/flux-3 #FLUX3 #multimodal #creativity #technology #innovation #HackerNews #ngated -
🚀 Welcome to FLUX 3, where we mash together images, videos, and sounds into one big #AI smoothie, because why not? 🎨🤖 Don't worry if you don't understand what "multimodal flow models" mean—neither does anyone else, but it sounds impressive in meetings! 💼👓
https://bfl.ai/blog/flux-3 #FLUX3 #multimodal #creativity #technology #innovation #HackerNews #ngated -
🚀 Welcome to FLUX 3, where we mash together images, videos, and sounds into one big #AI smoothie, because why not? 🎨🤖 Don't worry if you don't understand what "multimodal flow models" mean—neither does anyone else, but it sounds impressive in meetings! 💼👓
https://bfl.ai/blog/flux-3 #FLUX3 #multimodal #creativity #technology #innovation #HackerNews #ngated -
#BlackForestLabs released #Flux3, a #multimodal foundation model that learns from #images, #videos, and #audio. #Flux 3 can generate videos with native audio up to 20 seconds long and offers features like text-to-video and multilingual dialogue. The model is based on Self-Flow, a unified learning process that delivers better results than previous methods. https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs/?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
-
#BlackForestLabs released #Flux3, a #multimodal foundation model that learns from #images, #videos, and #audio. #Flux 3 can generate videos with native audio up to 20 seconds long and offers features like text-to-video and multilingual dialogue. The model is based on Self-Flow, a unified learning process that delivers better results than previous methods. https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs/?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
-
#BlackForestLabs released #Flux3, a #multimodal foundation model that learns from #images, #videos, and #audio. #Flux 3 can generate videos with native audio up to 20 seconds long and offers features like text-to-video and multilingual dialogue. The model is based on Self-Flow, a unified learning process that delivers better results than previous methods. https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs/?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
-
#BlackForestLabs released #Flux3, a #multimodal foundation model that learns from #images, #videos, and #audio. #Flux 3 can generate videos with native audio up to 20 seconds long and offers features like text-to-video and multilingual dialogue. The model is based on Self-Flow, a unified learning process that delivers better results than previous methods. https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs/?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
-
#BlackForestLabs released #Flux3, a #multimodal foundation model that learns from #images, #videos, and #audio. #Flux 3 can generate videos with native audio up to 20 seconds long and offers features like text-to-video and multilingual dialogue. The model is based on Self-Flow, a unified learning process that delivers better results than previous methods. https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs/?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
