Timlytogo

[el.cine @EHuanglu]

Loopy: New Audio-to-Video Lipsyncing Model Looks Insane

It generates lifelike facial expressions and movements from audio alone. It captures subtle details like sighs, expressive eyebrows, and natural head gestures, making your videos incredibly realistic.

Sample videos

1/5 Rapping statue

[Chris Boettcher @chrisboettcher9]

You breathe without thinking.

But 99% of people breathe incorrectly.

Here’s how to fix your breath for better physical performance, mental performance, and facial structure:

[Min Choi @minchoi]

Claude 3.5 Sonnet + Artifacts is a game changer.

People are now able to create apps, tools and more in wild use cases.

10 examples:

[Timlytogo @timlygo]

So fast!!!!

[kes @yoimnotkesku]

SearchGPT is pretty fast

[Timlytogo @timlygo]

@dify_ai @MyScaleDB I really like Dify, but there is one pain point: why is it not possible to run multiple tasks in parallel? Currently, your competitors, Coze and FastGPT, both support this feature. Can I submit this request to the engineering team? I look forward to using this feature soon.

[Timlytogo @timlygo]

Meta's new Llama 3.1 model is impressive, but demanding for local setups.
Recommending a free alternative: HuggingChat
• No installation needed
• Free and stable
• Instant access to latest AI
If you want to try LLAMA 3.1, check it out. Share your experience if you do!

[Timlytogo @timlygo]

Suno is absolutely mind-blowing. In the future, many musicians will lose their jobs because of Suno, but at the same time, more ordinary people will become musicians because of Suno.
#SunoAI #aimusic

[Suno @suno]

Available now: Stems 🥳 Pro & Premier users can now separate the vocals and instrumentals from songs, which will give you more control over how to use Suno.

1. Go to Library or Create, and click the vertical “...” on a song row
2. Click “Get Stems”
3. If you’re not there already, you’ll be navigated to the Create page where you can see two new clips that are generating. One will be the instrumentals, and the other will be the vocals. You can then download or extend each individual clip.

We’re so excited to see what you create!

❤️ Team Suno

[Timlytogo @timlygo]

This is the real open AI🫡 @OpenAI

[ollama @ollama]

Meet the Llama 3.1 family:

8B
ollama run llama3.1

70B
ollama run llama3.1:70b

405B
ollama run llama3.1:405b

More info:
https://t.co/0pBXvUsvuR

[Timlytogo @timlygo]

@aigclink 大佬，请问这个录屏用的是什么工具？效果真好啊

[Timlytogo @timlygo]

@godofprompt Hello, what tool was used to make the video in the tweet? 😂The effect is fantastic.

[Timlytogo @timlygo]

@MagnaDing Hello Magna , what tool was used to make the video in the tweet? The effect is fantastic.☺️

[Lyson Ober @lyson_ober]

两个星期前，我组织了 Dify 研究兴趣小组（自学）但我认为比学习工具本身更重要的是，去思考这些工具背后传递了怎样的理念与气质？而我们又想成为怎样的学习者？

1/

[ChatGPT @ChatGPT]

pushing the limits of intelligence we can serve for free is part of the quest to make sure AGI benefits all of humanity

[Timlytogo @timlygo]

@icreatelife I like this show!!!!!

[Timlytogo @timlygo]

@sprooos @OpenAI @tararezaeikh @dakotagoldberg @will_hath cool！！！

[Timlytogo @timlygo]

@sama when sora？

[Timlytogo @timlygo]

@MattVidPro too late!

[Tom Huang @tuturetom]

前 OpenAI 创始人，特斯拉自动驾驶团队负责人 @karpathy 新「AI + 教育」公司首秀课程 「LLM101n」大纲放出⚡️，课程还未发布，已经 21.3K Star ⭐️

特别期待！特别是编码部分使用「Python、C、Cuda」结合实现 🤩

感兴趣的推友可以订阅 Github 通知：-> https://t.co/j10Qa7GSlU