Bookoora.com

We enjoyed this AI-generated track so much, we decided to make Joe pretend-play it at a wine cellar. :) Enjoy the track. #aimusic

If you're wondering what ByteDance (makers of TikTok) is doing with Seedance 2.0 (instead of its global launch)... pandaily.com/byte-dance-lau…

Let the family decide. When the film comes out, let the audience decide. In between, yes, we should just leave matters be.

This is not generative AI.

@dustinhollywood @NAKIDpictures @Kling_ai @stages_ai Paused money for Seedance 2 Unpaused money and subscribe to Kling 3 instead

I know everyone is all about Seedance right now, but I wanna highlight how freaking good @Kling_ai is with V3. I made this for fun while I was watching The Hunt For Red October the other night lol 💪🔥🎥💻 I think both of these models are damn near close in all-around quality/adherence/and elements inclusion. It’s at the point now where access doesn’t matter, it’s truly time to put ideas to paper and push your vision. Any half measures means you’re behind now. Everyone should be writing not generating, that comes after. 🫣❤️🧠 only thing people are gonna take seriously is completed concepts. Then you take those concepts and go to the studios and pitch.. NOW IS THE MOMENT. Ai video doesn’t need to be the end goal, your film in bright lights, a red carpet, and physical theater can be and should be too 🙌✨ Made this with Kling v3 inside @stages_ai 👀 @NAKIDpictures

Australian tech entrepreneur used ChatGPT and AlphaFold to find a cancer cure for his dog. @GoogleDeepMind @OpenAI theaustralian.com.au/news/tech-boss…

Unfortunate for earnest AI users if true. reuters.com/technology/byt…

@heydin_ai It’s both ways. Not everyone can have nice things. Access should only be given to whitelisted users who have a good track record of not using it to generate copyrighted content. Maybe an intermediate party where genuine members are vetted might be a good start.

I just read this Reuters article about Seedance 2.0. Not sure if it’s fully confirmed or still speculation, but the content of the article feels very similar to the previous news when Disney raised copyright concerns about AI models. If it actually turns out that Seedance 2.0 doesn’t get released, that would be pretty disappointing considering how promising the tech looks for creators. Hopefully it’s just a delay while they sort things out behind the scenes. what do you guys think if it really ends up not being released? link in the comments below. 👇

@grok Is this supported on the Imagine API yet? :)

Create a video using up to 7 images in Grok Imagine. Include characters, places, objects, and more. Available on iOS, Android, and Web!

@mark_k @xai @grok So um when will we get last frame function?

Grok Imagine just got a major update from @xai! You can now specify up to 7 reference images for generating a video. The images can reference people, objects, or even keyframes. It's really very flexible! @Grok will then combine the references with your prompt into a video. 📹

So basically, companies pay Youtube to show ads and we pay Youtube to not show ads

@jordandchesney @yapper_so Yep we were halfway on episode 4 of our fantasy series and used SD2 briefly for some scenes. Had to pause and wait for now.

Will Seedance 2.0 be nerfed to death, or will it be the worlds greatest video generation mode to date? So much speculation going on right now. I've got the CEO of @yapper_so in my DM's telling me, "Are there content restrictions from ByteDance? Yes. Is it nerfed? No!" Meanwhile, @javilopen (who I very much trust and respect), is said to be in communication with ByteDance, and yet he is confirming that, "... almost all reference images that include a person are failing..." My experience - It's completely nerfed. If you're like me, you've got a half finished SD2 short film and no idea if you'll be able to finish it with SD2. My hope... ByteDance doesn't release until it is very much UN-NERFED. What do you think? Will SD2 make it?

Seedance 2.0 API pricing info. Take it what you will. :)

@javilopen Allow Seedance 2 to only allow image/video inputs generated from Seedance/Seedream. Guardrail conflict solved. Launch.

Good news is: I'm "working" (for free) with Seedance 2.0 to fix the moderation problem and stop the nerfed experience. I'm doing this for the glory of Generative AI. If you have feedback that can help Bytedance improve their models, leave a comment.

@OfficialLoganK @cgtwts We stopped using Vertex AI for this reason. We were charged way above what we budgeted for and were only notified too late when our soft limits were hit. A call to Google had our charges waived up to a limit but not all of it.

@cgtwts new hard caps experiment for the Gemini API should rollout targeting March 12, we have been sprinting to get this done to give devs more spend control and peace of mind!

They went from a $180 bill to losing $81,820 in 48 hours.

We tested this prompt on five music-generating platforms in this order (first 3 lets you download MVs for free): - Google Lyria 3 via Gemini (30 seconds) - Sonauto V3 - ProducerAI (now using Google Lyria v3) and - Suno v4.5 (MV is not free) - Udio (no downloads) While most follow the prompted sequences accurately, Sonauto goes a different route with a recurring overarching tune. Prompt: "An epic orchestral fantasy film score with a dynamic arc. Start: Eerie, minimalist opening with low-register double bass and haunting solo violin "teasing" a dark melody. Transition: Rapid crescendo into a high-energy battle anthem. Core: Driving taiko drum percussion, rhythmic string ostinatos, and soaring, emotionally-charged legato violin melodies. Crescendo: Grand cinematic finale featuring a powerful SATB choir (non-verbal chants) and full brass section. Ending: Sudden decrescendo into a "soft ripple" effect of delicate pizzicato strings and a faint, ethereal vocal hum. No synthesizers, no electronic processing, no lyrics." Suno v4.5 version: suno.com/s/zRTl4VAbFmjT… Udio version: udio.com/songs/rdfetWEz… #producerAI #sonauto #udio #suno #lyria #gemini #lyria3

It's pretty clear Veo 3.1 Fast needs an upgrade FAST. @GoogleAIStudio @FlowbyGoogle @GoogleDeepMind

@GoogleAIStudio @FlowbyGoogle @GoogleDeepMind

Unfortunate if true.