正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I can't believe this is open source. Wan 2.1 has great prompt coherence and the realism is really impressive for an open source model. This is image to video by the way.

Halim Alrasihi

14,333 subscribers

65,185 次观看 • 1 年前 •via X (Twitter)

科学技术艺术

Anya Rossi• Live Now

Private livecam show

12 条评论

drunkplato 的头像

drunkplato1 年前

16 fps makes it useless. they just had to add 8 more fps and they won.

Halim Alrasihi 的头像

Halim Alrasihi1 年前

This is not a big problem, you can just use an AI frame interpolation tool to fix this

AssemblyAI 的头像

AssemblyAI1 年前

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

the.PM 的头像

the.PM1 年前

I increasingly believe Ray2 is superior to Kling, the more I use Kling Pro.

maru 的头像

maru1 年前

The Chinese open source community is awesome!

Halim Alrasihi 的头像

Halim Alrasihi1 年前

It is!!

Lia Serra 的头像

Lia Serra1 年前

you are using it on your own machine ? how much vram and how long for a single video generation / fps / resolution please ?

Halim Alrasihi 的头像

Halim Alrasihi1 年前

I'm currently using @FAL, the resolution is 720p/16fps. The quality is great, even though you can clearly see the lack of frames, but I think it's okay. I'd rather have really good prompt coherence because you can always upscale and interpolate later.

Gadgetify 的头像

Gadgetify1 年前

It's definitely very realistic. Kling did a good job with the same prompt but Wan 2.1 is very impressive. By the way, has anyone tested their online interface?

Halim Alrasihi 的头像

Halim Alrasihi1 年前

Love this!

Timo 的头像

Timo1 年前

👀 wow

Halim Alrasihi 的头像

Halim Alrasihi1 年前

🙏❤️

相关视频

This is AI , It is so over !! ChatLLM now hosts Wan 2.1, an open-source video model that’s already better than SORA and as good as Google Veo-2 in quality but least censored Can we say China is leading in AI video and open-source both? How to use Wan 2.1 on ChatLLM in 30 sec.

This is AI , It is so over !! ChatLLM now hosts Wan 2.1, an open-source video model that’s already better than SORA and as good as Google Veo-2 in quality but least censored Can we say China is leading in AI video and open-source both? How to use Wan 2.1 on ChatLLM in 30 sec.

AshutoshShrivastava

124,086 次观看 • 1 年前

Quick AMV anime-style demo using the new WAN 2.1 'I2V' model on @FAL Its handling of 2D assets is impressive and fluid. Strong open-source performance from Wan

Quick AMV anime-style demo using the new WAN 2.1 'I2V' model on @FAL Its handling of 2D assets is impressive and fluid. Strong open-source performance from Wan

Kabooki AI Video

101,892 次观看 • 1 年前

The recording of the Wan 2.1 OPEN SOURCE release broadcast is now available

The recording of the Wan 2.1 OPEN SOURCE release broadcast is now available

Wan

35,511 次观看 • 1 年前

This is crazy... Stable Avatar can turn a single image + audio into a talking avatar video of infinite length. Open-source, built on Wan 2.1 and MIT Licensed. 8 wild examples:

Angry Tom

66,043 次观看 • 1 年前

Inferact cofounder Simon Mo: “I fundamentally believe that open source, especially how vLLM itself is structured, is critical to the AI infrastructure in the world. And what we want to do with Inferact is to support, maintain, steward and push forward the open source ecosystem.” “Open source moves so fast that the only way to stay ahead is adopting... And in fact this is exactly why we're staying all in on open source.” Simon Mo

Inferact cofounder Simon Mo: “I fundamentally believe that open source, especially how vLLM itself is structured, is critical to the AI infrastructure in the world. And what we want to do with Inferact is to support, maintain, steward and push forward the open source ecosystem.” “Open source moves so fast that the only way to stay ahead is adopting... And in fact this is exactly why we're staying all in on open source.” Simon Mo

a16z

29,383 次观看 • 6 个月前

Jason Calacanis: Anthropic, OpenAI and others are trying to kill OpenClaw Why? Because an open source agent platform is an existential threat to frontier model companies. @jason: “ People are going to say I'm a conspiracy theorist, but the number one goal, I believe, in the large language model, frontier model space, is to kill (OpenClaw). This is a giant movement to stop it, because this is the equivalent of having an open source Android-like player in the market, and that could be incredibly disruptive. Because, I believe, open source is going to win the day on the large language models and take 90% of the token usage, and I think the entire frontier model space could be undercut by open source. And I think they realize that SLMs, the smaller language models that are verticalized now, that will run on desktops and laptops and are even starting to run on the top ones, that is their biggest competitive threat, and I hope it happens.”

Jason Calacanis: Anthropic, OpenAI and others are trying to kill OpenClaw Why? Because an open source agent platform is an existential threat to frontier model companies. @jason: “ People are going to say I'm a conspiracy theorist, but the number one goal, I believe, in the large language model, frontier model space, is to kill (OpenClaw). This is a giant movement to stop it, because this is the equivalent of having an open source Android-like player in the market, and that could be incredibly disruptive. Because, I believe, open source is going to win the day on the large language models and take 90% of the token usage, and I think the entire frontier model space could be undercut by open source. And I think they realize that SLMs, the smaller language models that are verticalized now, that will run on desktops and laptops and are even starting to run on the top ones, that is their biggest competitive threat, and I hope it happens.”

The All-In Podcast

64,611 次观看 • 4 个月前

ELON: CHINA HAS THE BEST OPEN SOURCE AI MODELS RIGHT NOW “The best open source models are generally from China, which is bizarre. I think the second best one, or maybe it’s better than second best, is Grok 2.5. The open source model is actually very good, and we will continue to open source our models.” Source: The All-In Podcast

ELON: CHINA HAS THE BEST OPEN SOURCE AI MODELS RIGHT NOW “The best open source models are generally from China, which is bizarre. I think the second best one, or maybe it’s better than second best, is Grok 2.5. The open source model is actually very good, and we will continue to open source our models.” Source: The All-In Podcast

Mario Nawfal

1,163,582 次观看 • 9 个月前

Open Source is truely winning this time, Kimi literally cooked claude design on this... and it's 7x cheaper and 100% open source see the same prompt in the comments👇

Open Source is truely winning this time, Kimi literally cooked claude design on this... and it's 7x cheaper and 100% open source see the same prompt in the comments👇

Chidanand Tripathi

78,631 次观看 • 3 个月前

"Security by obscurity is going to zero rapidly." James O'Beirne and other researchers independently reproduced the COLDCARD vulnerability by pointing an AI model at the firmware history. This is the new reality for open-source security.

"Security by obscurity is going to zero rapidly." James O'Beirne and other researchers independently reproduced the COLDCARD vulnerability by pointing an AI model at the firmware history. This is the new reality for open-source security.

TFTC

13,879 次观看 • 9 天前

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training

Krea 2 Open-Source is now available on fal The most aesthetic open-source image model, released with open weights Turbo delivers fast, polished text-to-image at low step counts RAW serves as the malleable base checkpoint for LoRA training

fal

47,744 次观看 • 1 个月前

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

rob - comfyui

24,794 次观看 • 2 个月前

AI is out of control 🤣 Wan 2.1 14B model is the best open-source video model I have ever used. Been trying it on Novita AI Playground, and it's fast and the quality is good. - Better than SORA and close to Google Veo-2. - Other models like DeepSeek R1, V3, Hunyuan Video and more available.. - API access too. More details 👇

AI is out of control 🤣 Wan 2.1 14B model is the best open-source video model I have ever used. Been trying it on Novita AI Playground, and it's fast and the quality is good. - Better than SORA and close to Google Veo-2. - Other models like DeepSeek R1, V3, Hunyuan Video and more available.. - API access too. More details 👇

AshutoshShrivastava

74,350 次观看 • 1 年前

This new open-source voice model is wild Now AI-generated voice sounds more real than human Hard to believe this MrBeast voice is created with the new OpenAudio S1 AI Model Next-level storytelling. Next-level realism. Check this: MrBeast Mini-Roast “Never Doing This Again…”

This new open-source voice model is wild Now AI-generated voice sounds more real than human Hard to believe this MrBeast voice is created with the new OpenAudio S1 AI Model Next-level storytelling. Next-level realism. Check this: MrBeast Mini-Roast “Never Doing This Again…”

ZOYA ✪

26,309 次观看 • 1 年前

Thrilled to see Amazon Web Services making a major contribution to the open source AI community with the launch of the Strands Agents, an open source AI agents SDK! The core of Strands is the simple agentic loop that connects the model and tools together, like the two strands of DNA. This model-driven approach to agent building eliminates the need for complex agent orchestration by embracing the capabilities of state-of-the-art models to plan, chain thoughts, call tools, and reflect. Providing open source tools and interoperability with open source protocols is an important part of our strategy to enable an agentic future. Can't wait to see what you build with Strands!

Thrilled to see Amazon Web Services making a major contribution to the open source AI community with the launch of the Strands Agents, an open source AI agents SDK! The core of Strands is the simple agentic loop that connects the model and tools together, like the two strands of DNA. This model-driven approach to agent building eliminates the need for complex agent orchestration by embracing the capabilities of state-of-the-art models to plan, chain thoughts, call tools, and reflect. Providing open source tools and interoperability with open source protocols is an important part of our strategy to enable an agentic future. Can't wait to see what you build with Strands!

Swami Sivasubramanian

32,185 次观看 • 1 年前

In an AI world, effort is no longer the bottleneck—ideas are. Open-source AI enables anyone to have access to build anything they want without depending on the one-sided gates that closed-source offers. This is amplified by the open innovation that open-source development enables.

In an AI world, effort is no longer the bottleneck—ideas are. Open-source AI enables anyone to have access to build anything they want without depending on the one-sided gates that closed-source offers. This is amplified by the open innovation that open-source development enables.

Sentient

17,392 次观看 • 6 个月前

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

Santiago

44,783 次观看 • 1 年前

Local. Open weights. Native 4K. LTX-2 is now a 100% Open Source AI video model, and I tested it on my rig! Installation, VRAM usage, and the prompts I used for this video, below 👇

Local. Open weights. Native 4K. LTX-2 is now a 100% Open Source AI video model, and I tested it on my rig! Installation, VRAM usage, and the prompts I used for this video, below 👇

TechHalla

35,313 次观看 • 7 个月前

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 次观看 • 6 天前

We’re proving WAN 2.2 is worth it. It is now LIVE on Higgsfield. The most advanced open-source model is in Higgsfield for BOTH Video & Image. With 30+ viral presets to go with it. The FASTEST WAN 2.2 ever. Only on Higgsfield. Retweet to get a full guide in DMs. See how →

We’re proving WAN 2.2 is worth it. It is now LIVE on Higgsfield. The most advanced open-source model is in Higgsfield for BOTH Video & Image. With 30+ viral presets to go with it. The FASTEST WAN 2.2 ever. Only on Higgsfield. Retweet to get a full guide in DMs. See how →

Higgsfield AI 🧩

2,194,109 次观看 • 11 个月前