Загрузка видео...

Не удалось загрузить видео

На главную

🪄 Magi-1: The Autoregressive Diffusion Video Generation Model - Now available at 🥇 The first autoregressive video model with top-tier quality output 🔓 100% open-source & tech report 📊 Exceptional performance on major benchmarks ⏳ 1/5

SandAI_HQ's profile picture

Sand.ai

3,678 subscribers

914,585 просмотров • 1 год назад •via X (Twitter)

МузыкаНаука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Sand.ai
Sand.ai1 год назад

🔑 Key Features ✅ Infinite extension, enabling seamless and comprehensive storytelling across time ✅ Offers precise control over time with one-second accuracy      Going live for new web users today. Sign up at ⏳ 2/5

Фото профиля Sand.ai
Sand.ai1 год назад

🍾 Opening AI for all. Proud to support the open-source community. Explore our model. 💻 Github Page: 💾 Hugging Face: ⏳ 3/5

Фото профиля Sand.ai
Sand.ai1 год назад

🚰 Magi thoroughly understands the laws of physics. 🏆 Magi leads the Physics-IQ Benchmark with exceptional physics understanding ⏳ 4/5

Фото профиля Sand.ai
Sand.ai1 год назад

🙇 Thank you for reading. Come and join the @magiai_hq community. 👾 ⏳ 5/5

Фото профиля AshutoshShrivastava
AshutoshShrivastava1 год назад

Congratulations on the launch and great move open-sourcing it. 👏👏

Фото профиля Alex Volkov (Thursd/AI)
Alex Volkov (Thursd/AI)1 год назад

Yoo this is sick! Will mention on @thursdai_pod this week! Welcome to send someone to tell us about this 🔥

Фото профиля Gil
Gil1 год назад

amazing work, couldn't find the MAGI-1-4.5B. will it be released?

Фото профиля chris徒.eth
chris徒.eth1 год назад

Amazing！

Фото профиля Robin Delta
Robin Delta1 год назад

this is seriously next level tech wow

Фото профиля el.cine
el.cine1 год назад

looks unreal!

Похожие видео

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.
0:25

The first truly open-source audio-video model. LTX-2 is a DiT-based foundation model with all core video generation capabilities in one unified model. Designed to run locally on consumer GPUs. - text-to-video - image-to-video - and video-to-video modes 100% open-source.

Akshay 🚀

66,197 просмотров • 7 месяцев назад

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️
0:51

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

AI at Meta

122,001 просмотров • 2 лет назад

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks
1:51

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

46,962 просмотров • 7 месяцев назад

60-second AI video generation just got unlocked! LTXV is the first model to generate native long-form video, with controllability that beats every open source model. - 8× longer than typical gen video - 10–100× faster & cheaper - Runs even on consumer GPUs - Pose, depth & control LoRAs supported Available now. Go try it >>
1:00

60-second AI video generation just got unlocked! LTXV is the first model to generate native long-form video, with controllability that beats every open source model. - 8× longer than typical gen video - 10–100× faster & cheaper - Runs even on consumer GPUs - Pose, depth & control LoRAs supported Available now. Go try it >>

LTX

545,344 просмотров • 1 год назад

LTX 2.3 is out. Another big milestone for open-source video generation. Lightricks keeps pushing the frontier with faster, higher-quality video models the community can actually build with. Open video models are accelerating fast. Model:
1:17

LTX 2.3 is out. Another big milestone for open-source video generation. Lightricks keeps pushing the frontier with faster, higher-quality video models the community can actually build with. Open video models are accelerating fast. Model:

Hugging Models

35,935 просмотров • 5 месяцев назад

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.
0:22

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

NVIDIA AI

31,412 просмотров • 1 месяц назад

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵
1:06

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

Chubby♨️

37,776 просмотров • 8 месяцев назад

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.
1:17

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

DailyPapers

41,727 просмотров • 3 месяцев назад

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise customers and Creative Partners. Learn more about Act-Two below. 1/4
1:11

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise customers and Creative Partners. Learn more about Act-Two below. 1/4

Runway

499,790 просмотров • 1 год назад

LTX-2 is the first truly open-source audio-video generation model, and it's extremely impressive. Production-grade, native 4K 50 FPS output generated entirely on your own hardware. 2,382,172 Hugging Face downloads in the last month says it all. LTX 👏
1:00

LTX-2 is the first truly open-source audio-video generation model, and it's extremely impressive. Production-grade, native 4K 50 FPS output generated entirely on your own hardware. 2,382,172 Hugging Face downloads in the last month says it all. LTX 👏

Roberto Nickson

39,551 просмотров • 7 месяцев назад

Super excited to introduce Pandora, a generative video World Model interactively controllable by language. #Sora and #GPT4 are both powerful. How about fusing them in a single model? 💥 Pandora gives a preview:🔭 > Build a General World Model (GWM) super efficiently by integrating pretrained autoregressive LLM and diffusion Video Model, aligning them in the representation space. > Let the LLM control the VM on-the-fly. Instruction tuning maximizes the controllability. > Autoregressive LLM empowers VM to generate indefinitely long videos: Starting with a VM for 2-second videos, Pandora extends it for 8-second videos. Would #Sora+#GPT4 under Pandora produce hours-long videos? 📽️ > World Model is beyond just video generation. It’s sensory-level information processing + concept-level reasoning and reflection. Pandora bridges both, with the concept- / language-level backbone (LLM) managing & steering the sensory-level VM functionalities. 👁️🧠 Check out for a bunch of interesting results:
1:35

Super excited to introduce Pandora, a generative video World Model interactively controllable by language. #Sora and #GPT4 are both powerful. How about fusing them in a single model? 💥 Pandora gives a preview:🔭 > Build a General World Model (GWM) super efficiently by integrating pretrained autoregressive LLM and diffusion Video Model, aligning them in the representation space. > Let the LLM control the VM on-the-fly. Instruction tuning maximizes the controllability. > Autoregressive LLM empowers VM to generate indefinitely long videos: Starting with a VM for 2-second videos, Pandora extends it for 8-second videos. Would #Sora+#GPT4 under Pandora produce hours-long videos? 📽️ > World Model is beyond just video generation. It’s sensory-level information processing + concept-level reasoning and reflection. Pandora bridges both, with the concept- / language-level backbone (LLM) managing & steering the sensory-level VM functionalities. 👁️🧠 Check out for a bunch of interesting results:

Zhiting Hu

63,477 просмотров • 2 лет назад

Veo: our most capable video generation model is now available on Vertex AI in private preview! Developed by Google DeepMind, Veo generates high-quality videos based on text or image prompts in a range of cinematic & visual styles with exceptional speed →
0:25

Veo: our most capable video generation model is now available on Vertex AI in private preview! Developed by Google DeepMind, Veo generates high-quality videos based on text or image prompts in a range of cinematic & visual styles with exceptional speed →

Google Cloud

190,874 просмотров • 1 год назад

NEW VIDEO: every major AI model ranked for vibe coding. Fable 5 is still the only S tier. Opus 5 redeemed itself to A tier. Grok 4.6 is B tier with the best subscription in AI. Real world rankings from someone who spends over $1,000 a month on AI subscriptions. Not benchmarks. I do not recommend anything below B tier.
27:44

NEW VIDEO: every major AI model ranked for vibe coding. Fable 5 is still the only S tier. Opus 5 redeemed itself to A tier. Grok 4.6 is B tier with the best subscription in AI. Real world rankings from someone who spends over $1,000 a month on AI subscriptions. Not benchmarks. I do not recommend anything below B tier.

BridgeMind

19,420 просмотров • 4 дней назад

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: Paper: It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.
1:30

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: Paper: It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.

Ceyuan Yang

77,551 просмотров • 1 год назад

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵
1:02

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵

Mihir Prabhudesai

80,875 просмотров • 1 месяц назад

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.
2:25

Congrats to LemonSlice on their $10.5M seed! They built the world's first interactive talking AI video model—a face layer for voice agents. Trained on a custom, 20B-parameter video diffusion transformer, streaming at 20fps on a single GPU. Infinite-length video generation with no error accumulation.

Y Combinator

50,944 просмотров • 8 месяцев назад

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:
1:03

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:

Tencent Hy

128,008 просмотров • 9 месяцев назад

Generate Songs with HeartMuLa, with 8GB VRAM! HeartMuLa is the latest open source song generation AI model everyone's raving about. But the default model couldn't run on low VRAM machines. Then WanGP just made it work with just 8GB VRAM! 1-Click Install on Pinokio.
0:47

Generate Songs with HeartMuLa, with 8GB VRAM! HeartMuLa is the latest open source song generation AI model everyone's raving about. But the default model couldn't run on low VRAM machines. Then WanGP just made it work with just 8GB VRAM! 1-Click Install on Pinokio.

cocktail peanut

27,848 просмотров • 7 месяцев назад