Videre

@topazlabs Premiere

Adobe Premiere users, what if you could bring Topaz video upscaling and enhancement directly to the timeline? Check out this tech demo that would allow you to add clips, choose models like Proteus or Starlight, render, and keep working. Enhanced media would drop back into your sequence automatically. Interested in a future beta? Comment "Premiere" here, message us, or visit us at NAB next week, booth N2773. @Adobe

@FussyPastor @higgsfield @freepik been using @FlowbyGoogle for NB2 generations for free and endless generations. plus, their latest UI update has been a huge addition to how I do my workflows.

@higgsfield @freepik So which platform, besides Higgsfield, offers Nano Banana 2 unlimited on a decent plan? Moving on from @freepik.

I recently switched from @higgsfield to @freepik due to Higgy's shit business practices like bait and switching unlimited access. First thing I encounter, them taking away the entire reason I subscribed with them... Thanks for telling me "what I need" is to be monetized more.

@iamneubert any promo for new users? wanna test it out

The (current) Next-Gen Video model, now available on Runway. Go have some fun today!

@FlowbyGoogle I didn't know that the @ feature was there, haha. I have been using Flow since then for projects. Thanks for adding new workflows and making it easy for us creators to create content.

Flow just dropped an exciting update last week, so let’s dive in and explore what’s possible. In this tutorial, you will learn to seamlessly create, refine, and compose your stories. With Flow, you can generate and edit images and videos in a single workflow, allowing you to build cohesive narratives with consistency. Here’s a look at how you can create with Flow:

@Kling_ai Kling AI Avatar

🎉Introducing Kling AI Avatar! Any Role, Any Voice! Simply add your Avatar image and audio, and prompt the emotions and expressions to bring your Avatar to life! Limited access only upon launch. Comment "Kling AI Avatar" & Repost to get early access! #klingai #klingavatar

@oran_ge I want to test this!

最近我一直在内测一款非常惊艳的 AI Agent 产品，今天终于可以官宣了！ Lovart：全球首个设计 Agent 。 这是 4o 生图之后文生图领域最有想象力的文生图产品形态。 设计 Agent 到底是什么？ - 设计全链路，从任务拆解和分步骤执行，一句话搞定 - 图像视频音乐模型全接入，自由调度 - 生成图像自动分离文字图层，随心修改 设计 Agent 初体验： 感谢 @lovart_ai 官方在上周邀请我参与产品内测，这是我的一些使用体验，供大家参考。 图1: 我可以让它根据我家猫的照片做一套银渐层表情包，它会自己设计表情，挨个生图，还可以全部编辑，设计出黑底渐变色版本。 图2: 为宣传智能家居扬声器的 30 秒视频广告创建一个 6 帧故事板。 它会先根据需求，写出故事，然后开始进行角色设计。 完成之后，会进行关键场景的设计。 在最后把场景填充到故事板里，为每个画面配上光线、摄影机移动等信息。 图3: 我让它为一个名为 "VIVIDPIX "的新生活科技品牌创建跨媒体发布活动。它不仅设计了logo、海报、周边，还用可灵制作了3D版本的logo动画，用suno制作了bgm。 由于所有的模型都拥有相同的 Context，配合起来丝滑无比。 图4: 在海报的生成中，最大的痛点是文字后期的编辑，Lovart 很好地解决了这一痛点。 我这里为一种新的植物蛋白饮料设计一张宣传海报。 一分钟后，它就生成了左侧的标准海报，同时在右侧附上了图文分离的版本。 现在我可以自由修改文字的内容、大小颜色，非常方便。 以上就是 Lovart AI 的初体验，接下来还会尝试一句话出产品宣传视频，可以关注后续更新。 这个产品目前还在内测阶段，如果你也想体验，可以直接留言，我这里有一些邀请码会发给你。 也可以在这里加入 waitlist：lovart.ai

@macwhisperapp I just noticed that one or two (plus that one beta feature in the app itself) of these options mess up (30-40%) the transcription, regardless of which model I'm using. Also, the feedback button now leads me to nothing. I'm not sure why, but it worked before.

@0xraspberrycat take your time

@0xraspberrycat llm

@ShotsAppHQ 👋

The next big step for Shots is here—now in private beta! Want to try it out? Drop a 👋 below, and we’ll send you an invite.

@pie6k having the capability to adjust the audio from the timeline similar to Riverside would be awesome @skirano

Would it be useful for you if Screen Studio could capture screenshots instead of recording videos? It would then create an empty project in which you could manually add zooms, etc.

@jordibruin As always, @jordibruin Thank you so much for this! Hopefully it fixes the random crashes while using it or recording a meeting + frequent stuck moments using the Large V3 model.

MacWhisper 11.10 is available now with support for ElevenLabs Scribe & Deepgram Nova (both including speaker recognition), support for OpenRouter and a ton of quality of life improvements!

@pie6k Alright, you got me to renew again @pie6k. Time to explore the new updates from 2024

Someone noticed!

@fixkeyai I sent a message to support last year but still no response. It is not working properly on my Mac 🥲 I bought the 1-year subscription, btw, expiring on Feb this year

Fixkey Voice is here – Free speech-to-text is now generally available for everyone! Press Fn Start talking Release Get the text pasted back!

@fofrAI Nooooo oooooo

Sora signups are open again

@jordibruin Thank you so much @jordibruin, but I only wonder if there's a shortcut key for "Record App Audio" that is similar to with how the shortcut key (shift+cmd+G) "Global" works. That alone will be a great addition

Automatic meeting recording coming to MacWhisper before the end of the year

@fofrAI Damn. I admire your mind for coming up with these ideas. Looks natural imo. Also, it somehow looks like your profile picture as well 😂

@fofrAI Yours looks like it's actually a real photo, not AI. I'm not getting anywhere near this 😅 Might have to run several times more

If you suffix a simple prompt to a filename, you can guide the Flux Pro output to something you want without losing the realism: Try, "IMG_0134.CR2: a dog" or ""IMG_0134.CR2: a cat" replicate.com/p/qkapcw5h6srg… Using 1.1 Pro: replicate.com/black-forest-l…

@jordibruin Damn. Jordi and the team ftw always! I just saw a post about the new model and planning to tag you but I guess I don’t have to anymore 😂 Thank you so much @jordibruin 🫡

MacWhisper now supports the new Whisper Turbo model! 21x times realtime on an M3 Pro 🏃💨 macwhisper.com

@jordibruin I agree. It feels so weird to see a bot joining the room during meetings. I still prefer taking notes using the Notes app and recording them with MacWhisper. Then, use the AI tab to give pointers or summarize the entire meeting without the information leaving my laptop.

Another reason to use local transcription with MacWhisper 🙂 macwhisper.com