正在加载视频...

视频加载失败

返回首页

We are launching a new stealth model - "Andromeda Alpha" This is a smaller reasoning model that has been trained to be really good at image understanding.

OpenRouter's profile picture

OpenRouter

94,153 subscribers

42,403 次观看 • 11 个月前 •via X (Twitter)

新闻政治科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Centering a div is now a solved problem Developers have been testing the fleX Alpha stealth model. today, we are announcing it as DIV-1 Flash DIV-1 Flash delivers frontier-level alignment at a fraction of the cost Full benchmarks bellow ↓
0:12

Centering a div is now a solved problem Developers have been testing the fleX Alpha stealth model. today, we are announcing it as DIV-1 Flash DIV-1 Flash delivers frontier-level alignment at a fraction of the cost Full benchmarks bellow ↓

Kevin Grajeda

625,821 次观看 • 25 天前

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this
0:10

Okay this new model is insane. Generate an image, then give it to the model to turn it into a 3D model with matching texture in seconds. Creativity on Spielwerk will be endless with this

Eike Drescher

37,987 次观看 • 10 个月前

NEWS: Tesla has announced that the new larger Model Y L is launching in Thailand.
0:17

NEWS: Tesla has announced that the new larger Model Y L is launching in Thailand.

Sawyer Merritt

154,476 次观看 • 6 个月前

The new Wan 2.7 image to video model. LOL WUT?🤣 Why even release a junk model such as this when the world now has Seedance 2??
0:10

The new Wan 2.7 image to video model. LOL WUT?🤣 Why even release a junk model such as this when the world now has Seedance 2??

Christopher Gwinn | Grindhouse Glitch

21,792 次观看 • 5 个月前

We may have a new best image-to-video model 👀 I’ve been testing Kling 2.0 more and am really impressed with the results. Veo 2 was previously best-in-class (IMO), but Kling has more motion and maintains coherence.
0:15

We may have a new best image-to-video model 👀 I’ve been testing Kling 2.0 more and am really impressed with the results. Veo 2 was previously best-in-class (IMO), but Kling has more motion and maintains coherence.

Justine Moore

41,669 次观看 • 1 年前

We got a sneak peek at the Masters app’s new AI commentary, which’ll be live this week. @IBMWatson has trained a language model to learn golf and deliver insights in real time like an announcer would. Here’s an example of what it’ll sound like.
0:17

We got a sneak peek at the Masters app’s new AI commentary, which’ll be live this week. @IBMWatson has trained a language model to learn golf and deliver insights in real time like an announcer would. Here’s an example of what it’ll sound like.

Stephen Hennessey

2,617,603 次观看 • 3 年前

The new open-weights Hailuo AI (MiniMax) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.
0:15

The new open-weights Hailuo AI (MiniMax) H3 is live on OpenRouter thanks to MiniMax (official)! H3 is a lightweight video model for text, image, audio, & video input, with native audio-visual output. Built for instruction-led edits, text/brand rendering, and video-2-video motion transfer.

OpenRouter

22,767 次观看 • 1 个月前

We released a new model 🎉 !!! Firefly Image 2 !!!! As a scientist I am in disbelief that such model is possible with a small dataset as we had. We compensated artists for training it. We worked very hard on it. Please, enjoy! #AdobeMax
0:16

We released a new model 🎉 !!! Firefly Image 2 !!!! As a scientist I am in disbelief that such model is possible with a small dataset as we had. We compensated artists for training it. We worked very hard on it. Please, enjoy! #AdobeMax

Kris Kashtanova

200,492 次观看 • 2 年前

🔥Meshy Image to 3D has achieved a major breakthrough once again! We've boosted the generation speed by 20x, making it effortless to obtain a 3D model in just about 60 seconds. No more wait, Image-to-model transformation has never been this lightning-fast! 🔥🚀 Try Meshy image to 3D on Discord now: #3DModeling #GenerativeAI #MeshyAI
0:12

🔥Meshy Image to 3D has achieved a major breakthrough once again! We've boosted the generation speed by 20x, making it effortless to obtain a 3D model in just about 60 seconds. No more wait, Image-to-model transformation has never been this lightning-fast! 🔥🚀 Try Meshy image to 3D on Discord now: #3DModeling #GenerativeAI #MeshyAI

MeshyAI

35,533 次观看 • 2 年前

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:
0:10

The Stable Video Diffusion model just dropped 🔥 The new model supports: – Text-to-Video – Image-to-Video – 14 or 25 frames at 576 x 1024 – Multi-View Generation – Frame Interpolation – 3D Scene Understanding – Camera Control via LoRA Paper: Code: SVD model: SVD-XT model:

Dreaming Tulpa 🥓👑

457,795 次观看 • 2 年前

i gave Ox Alpha the main menu from ECHO and asked it to recreate it only ONE (1) prompt was enough to build this, using the reference this is one of the most beautiful output i've ever had from any model the fact that it's from a stealth model is mindblowing
0:18

i gave Ox Alpha the main menu from ECHO and asked it to recreate it only ONE (1) prompt was enough to build this, using the reference this is one of the most beautiful output i've ever had from any model the fact that it's from a stealth model is mindblowing

filipe

31,171 次观看 • 27 天前

Excited to launch GPT-5 on OpenRouter! 🧠dynamic reasoning ("think hard about this!") 🧑‍💻 much better frontend design and debugging 🏥 OpenAI's best model for health-related questions Details 👇
0:13

Excited to launch GPT-5 on OpenRouter! 🧠dynamic reasoning ("think hard about this!") 🧑‍💻 much better frontend design and debugging 🏥 OpenAI's best model for health-related questions Details 👇

OpenRouter

32,918 次观看 • 1 年前

this is the BEST vision language model I have ever tried! Aria is a new model by Rhymes.AI: a 25.3B multimodal model that can take image/video inputs 🤩 They release the model with Apache-2.0 license and fine-tuning scripts as well 👏 I tested it extensively, keep reading to learn more 🧶
0:10

this is the BEST vision language model I have ever tried! Aria is a new model by Rhymes.AI: a 25.3B multimodal model that can take image/video inputs 🤩 They release the model with Apache-2.0 license and fine-tuning scripts as well 👏 I tested it extensively, keep reading to learn more 🧶

merve

176,125 次观看 • 1 年前

Nano Banana is not Google’s model, it's from Higgsfield. They built it to be the image engine that feeds their new Kling integration. The results are insane.
0:10

Nano Banana is not Google’s model, it's from Higgsfield. They built it to be the image engine that feeds their new Kling integration. The results are insane.

FELIX

52,617 次观看 • 1 年前

Google has just launched an AI feature capable of planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵
0:14

Google has just launched an AI feature capable of planning, reasoning and searching the web. All this is done in a single prompt using Deep Research. This is literally the first reasoning model that has access to the internet. Game-changer. How to use it below 🧵

Paul Couvert

298,330 次观看 • 1 年前

NEWS: The Model Y L is launching soon in South Korea, according to a new regulatory filing.
0:12

NEWS: The Model Y L is launching soon in South Korea, according to a new regulatory filing.

Sawyer Merritt

208,727 次观看 • 6 个月前

Canter 2B is a photography-oriented text-to-image model being trained on just a single GPU by data-archetype 🐎 are we entering the indie ai models era? still training, the v0002 checkpoint is available, more to come ▶️ play on spaces
0:19

Canter 2B is a photography-oriented text-to-image model being trained on just a single GPU by data-archetype 🐎 are we entering the indie ai models era? still training, the v0002 checkpoint is available, more to come ▶️ play on spaces

Hugging Apps

24,291 次观看 • 27 天前

Flow Reasoning Models are looped models. In our recent work, we turn a flow model into a recurrent model to solve reasoning problems (e.g. Sudoku). Predictions are fed back as inputs and iteratively refined. Each pass gets its own local loss. No backprop through time.
0:19

Flow Reasoning Models are looped models. In our recent work, we turn a flow model into a recurrent model to solve reasoning problems (e.g. Sudoku). Predictions are fed back as inputs and iteratively refined. Each pass gets its own local loss. No backprop through time.

Alec Helbling

33,269 次观看 • 4 天前