Blaine Brown's banner

Blaine Brown

@blizaine • 16,643 subscribers

Founder @InflectionLabs_ • 850k+ followers across socials • GenAI Creative • Creator of @AskiLean • ProAV • Favikon Global Top AI 200 Influencer

Shorts

Seedance 2.0 - So amazing! Need to work on Force choke prompting though

Seedance 2.0 - So amazing! Need to work on Force choke prompting though

330,721 次观看

4o is getting nerfed. Stuff that worked yesterday no longer works. 😞 @openai & Sam Altman keep 4o awesome please! 🙏

4o is getting nerfed. Stuff that worked yesterday no longer works. 😞 @openai & Sam Altman keep 4o awesome please! 🙏

551,615 次观看

The motion brush in Kling AI is really good! 🔊🔊

The motion brush in Kling AI is really good! 🔊🔊

673,156 次观看

My wife & I standing in line for VelociCoaster at Universal Studios & this happens!

My wife & I standing in line for VelociCoaster at Universal Studios & this happens!

392,257 次观看

Look how far we've come! I found one of the first clips I created with PIKA Labs via Discord in 2023. Both of these are SOTA for their time 🤯 Seedance 2.0 - Superman vs Wolverine

Look how far we've come! I found one of the first clips I created with PIKA Labs via Discord in 2023. Both of these are SOTA for their time 🤯 Seedance 2.0 - Superman vs Wolverine

63,592 次观看

Hahaha! Kling 2.0 is crazy good! The girlfriend is not happy!

Hahaha! Kling 2.0 is crazy good! The girlfriend is not happy!

106,509 次观看

Sometimes Seadance 2.0 kills me 💀

Sometimes Seadance 2.0 kills me 💀

34,207 次观看

Runway Aleph is still blowing my mind. Tutorial: Split into 3 clips. Prompt: Keep the actor, office architecture and camera movements the same, but add fast flowing rapids through the hallways.

Runway Aleph is still blowing my mind. Tutorial: Split into 3 clips. Prompt: Keep the actor, office architecture and camera movements the same, but add fast flowing rapids through the hallways.

69,877 次观看

Another Seedance 2.0 test. It took me a few views before I noticed the kid's legs in the cart.😭

Another Seedance 2.0 test. It took me a few views before I noticed the kid's legs in the cart.😭

30,009 次观看

Runway Act-One vs Kling w/ LivePortrait. I'm trying to create a music video about a vampire who has lived for centuries; called Endless Nights. Runway wouldn't let me run an image w/ blood, so I removed it for this test. I also animated the image using Kling & LivePortrait.

Runway Act-One vs Kling w/ LivePortrait. I'm trying to create a music video about a vampire who has lived for centuries; called Endless Nights. Runway wouldn't let me run an image w/ blood, so I removed it for this test. I also animated the image using Kling & LivePortrait.

65,347 次观看

Watch this brown bear improve his dancing skills as we change the Sora Remix level from Strong (8) to Mild (6). Sora Remix (Video-to-Video) is crazy good 🤯

Watch this brown bear improve his dancing skills as we change the Sora Remix level from Strong (8) to Mild (6). Sora Remix (Video-to-Video) is crazy good 🤯

55,229 次观看

How it started How it’s going

How it started How it’s going

42,805 次观看

Here's a Veo2 prompt enhancer GPT. Link in thread 🧵 It works well for other GenAI platforms, too! Give it a simple prompt, and it will output an enhanced one. It does this by referencing many high-quality example prompts. It also helps with character consistency.

Here's a Veo2 prompt enhancer GPT. Link in thread 🧵 It works well for other GenAI platforms, too! Give it a simple prompt, and it will output an enhanced one. It does this by referencing many high-quality example prompts. It also helps with character consistency.

35,748 次观看

Hey! I have a few Sora 2 invite codes. Like, follow & repost this thread and turn on notifications. I’ll drop the first code in about 20 min to this thread. Bookmark! This was my first test 🤯😆

Hey! I have a few Sora 2 invite codes. Like, follow & repost this thread and turn on notifications. I’ll drop the first code in about 20 min to this thread. Bookmark! This was my first test 🤯😆

16,102 次观看

I’ve used all the recent GenAI video models extensively & here’s my 2¢: 🎬 Runway Gen3 Alpha - best image quality & motion for text-to-video & embedded words. Great at prompt travel changes over the course of 10 sec. And I’m super bullish on how gen3 will evolve, hopefully adopting the features listed below. Kling - best quality for image-to-video with prompt control, like eating food. Great clip extension that accounts for character (ie walking stride) & camera movement (speed & angle), rather than just using final frame. But it’s limited availability & Chinese native language is limiting. Used for Spider-Man video below (via Midjourney). LumaLabs - best for keyframe start & end control (it can not be overstated how important this is. other services should add it ASAP!) and their high dynamic action movements are really fun. Luma was used in my viral Multiverse of Memes video. PikaLabs - they haven’t gotten as much attention as others lately. But they did update their video model a few weeks ago and it looks great. Also, they are notable for their unique & AWESOME features, like video in-painting & out-painting. My perfect AI video platform would have the following features: 1) Gen3’s quality, prompt control & text embedding. 2) KLing’s image-to-video quality, prompt control & clip extension quality. 3) Luma’s multi-keyframe control & dynamic movement ability. 4) Pika’s inpainting & outpainting ability. And a video-to-video (aka next-gen Runway gen1) could be a game changer, too. It’s an exciting time to be alive 🫶 Who will get there first? 🔉🔉

I’ve used all the recent GenAI video models extensively & here’s my 2¢: 🎬 Runway Gen3 Alpha - best image quality & motion for text-to-video & embedded words. Great at prompt travel changes over the course of 10 sec. And I’m super bullish on how gen3 will evolve, hopefully adopting the features listed below. Kling - best quality for image-to-video with prompt control, like eating food. Great clip extension that accounts for character (ie walking stride) & camera movement (speed & angle), rather than just using final frame. But it’s limited availability & Chinese native language is limiting. Used for Spider-Man video below (via Midjourney). LumaLabs - best for keyframe start & end control (it can not be overstated how important this is. other services should add it ASAP!) and their high dynamic action movements are really fun. Luma was used in my viral Multiverse of Memes video. PikaLabs - they haven’t gotten as much attention as others lately. But they did update their video model a few weeks ago and it looks great. Also, they are notable for their unique & AWESOME features, like video in-painting & out-painting. My perfect AI video platform would have the following features: 1) Gen3’s quality, prompt control & text embedding. 2) KLing’s image-to-video quality, prompt control & clip extension quality. 3) Luma’s multi-keyframe control & dynamic movement ability. 4) Pika’s inpainting & outpainting ability. And a video-to-video (aka next-gen Runway gen1) could be a game changer, too. It’s an exciting time to be alive 🫶 Who will get there first? 🔉🔉

26,534 次观看

First test of LatentSync; an open source lip sync tool 🔥 Link in thread 🧵 It only requires a source video and a spoken audio clip. 🔊 Google Veo2: video clips E2-F5-TTS: Text to Speech (o/s) LatentSync: Lip sync (o/s) MMAudio: Background SFX (o/s)

First test of LatentSync; an open source lip sync tool 🔥 Link in thread 🧵 It only requires a source video and a spoken audio clip. 🔊 Google Veo2: video clips E2-F5-TTS: Text to Speech (o/s) LatentSync: Lip sync (o/s) MMAudio: Background SFX (o/s)

21,262 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

OMG! Anything is possible now! 🤣 Fan fiction is going to new levels by combining these tools: • Nano Banana Pro for images & scene consistant camera angles • VEO3.1 for video • E2/F5 TTS (Open Source Voice Cloning) • Sound Effects 🔊🔊🆙

OMG! Anything is possible now! 🤣 Fan fiction is going to new levels by combining these tools: • Nano Banana Pro for images & scene consistant camera angles • VEO3.1 for video • E2/F5 TTS (Open Source Voice Cloning) • Sound Effects 🔊🔊🆙

2,628,843 次观看 • 6 个月前

With Pika v1.5 you can basically be James Cameron.

With Pika v1.5 you can basically be James Cameron.

6,021,945 次观看 • 1 年前

Real-time Latent Consistency is next-level fun! I can't get enough! I forked & modified the main GitHub repo & added Desktop/App Capture as well as batch scripts for easy installation and launching. Info in thread. 👇

Real-time Latent Consistency is next-level fun! I can't get enough! I forked & modified the main GitHub repo & added Desktop/App Capture as well as batch scripts for easy installation and launching. Info in thread. 👇

5,962,104 次观看 • 2 年前

Insane! 🤯 Luma AI Dream Studio clips can be infinitely long by grabbing the last frame & generating a follow up clip. Unlike most other AI video tools that loose quality & morph; Dream Studio just keeps it going forever. This is 14 continuous clips. Sound up 🆙🔊🔊

Insane! 🤯 Luma AI Dream Studio clips can be infinitely long by grabbing the last frame & generating a follow up clip. Unlike most other AI video tools that loose quality & morph; Dream Studio just keeps it going forever. This is 14 continuous clips. Sound up 🆙🔊🔊

3,372,599 次观看 • 2 年前

Image the possibilities with Runway Gen3’s new Expand feature. This almost seems impossible. 🤯 (view full on mobile)

Image the possibilities with Runway Gen3’s new Expand feature. This almost seems impossible. 🤯 (view full on mobile)

1,985,821 次观看 • 1 年前

This is insane!🔥 This is a 720p (2D) video I shot of my kids 15 years ago! I used AI to upscale it, depth-map it, & used the depth map to convert it to 3D SBS, & then converted that to Spatial Video for Apple Vision Pro (MV-HEVC). My son is currently a senior in high school, and my daughter is a sophomore in college. This video has complete spatial depth when viewed in the Apple Vision Pro. Obviously, you can't appreciate that via this post. But it's like I'm there & I can see into this room. Talk about giving you the feels.🥹 This can be done with ANY video. 🤯 I'm working on refining the workflow, as it's a bit cumbersome. I plan to share it, but holy cow! I had to post this.

This is insane!🔥 This is a 720p (2D) video I shot of my kids 15 years ago! I used AI to upscale it, depth-map it, & used the depth map to convert it to 3D SBS, & then converted that to Spatial Video for Apple Vision Pro (MV-HEVC). My son is currently a senior in high school, and my daughter is a sophomore in college. This video has complete spatial depth when viewed in the Apple Vision Pro. Obviously, you can't appreciate that via this post. But it's like I'm there & I can see into this room. Talk about giving you the feels.🥹 This can be done with ANY video. 🤯 I'm working on refining the workflow, as it's a bit cumbersome. I plan to share it, but holy cow! I had to post this.

1,468,332 次观看 • 2 年前

Did guys you see Thanos on Joe Rogan Podcast News podcast? He seems like a pretty good dude, tbh.

Did guys you see Thanos on Joe Rogan Podcast News podcast? He seems like a pretty good dude, tbh.

869,433 次观看 • 1 年前

Me, every time I get in a pool... (via Runway Aleph)

Me, every time I get in a pool... (via Runway Aleph)

436,749 次观看 • 10 个月前

This is the best Open Source TTS available on Mac right now. Watch Peter break it down. I combined two Qwen3-TTS projects. One for MLX speed & the other for its beautiful UI (but was slow on Mac). Then added a bunch of features. Qwen3-TTS-MLX-WebUI-Enhanced Install via Pinokio

This is the best Open Source TTS available on Mac right now. Watch Peter break it down. I combined two Qwen3-TTS projects. One for MLX speed & the other for its beautiful UI (but was slow on Mac). Then added a bunch of features. Qwen3-TTS-MLX-WebUI-Enhanced Install via Pinokio

167,095 次观看 • 3 个月前

what would you call this sitcom? 🔊🎶

what would you call this sitcom? 🔊🎶

562,962 次观看 • 1 年前

It was a busy day on the set of Avengers Doomsday! Thread: How to do this quickly & easily with Nano Banano Pro & Kling v2.6, including prompts. 👇

It was a busy day on the set of Avengers Doomsday! Thread: How to do this quickly & easily with Nano Banano Pro & Kling v2.6, including prompts. 👇

148,739 次观看 • 5 个月前

Let’s have a good old fashioned GenAI steak-off! 🥩 This test is very challenging for AI models. Hands, consecutive slicing physics & movement, interpretation of ‘steak done perfectly’, steam, juices, etc. Who did it best? Who’s your top three?

Let’s have a good old fashioned GenAI steak-off! 🥩 This test is very challenging for AI models. Hands, consecutive slicing physics & movement, interpretation of ‘steak done perfectly’, steam, juices, etc. Who did it best? Who’s your top three?

394,226 次观看 • 1 年前

I love that we can use AI to create fan fiction based on movies that haven’t come out yet. Here’s a quick Fantastic Four team-up clip, featuring the new cast, coming in 2025 to the MCU. 🔊🔊

I love that we can use AI to create fan fiction based on movies that haven’t come out yet. Here’s a quick Fantastic Four team-up clip, featuring the new cast, coming in 2025 to the MCU. 🔊🔊

477,280 次观看 • 1 年前

This is the best open source text-to-speech I’ve ever heard. It’s free and you can run it locally. It’s also unrestricted as you can give it any voice sample. In this video I have it speak as Peter Griffin, Trump, Jarvis, & Scarjo’s voice from HER. More in thread 👇

This is the best open source text-to-speech I’ve ever heard. It’s free and you can run it locally. It’s also unrestricted as you can give it any voice sample. In this video I have it speak as Peter Griffin, Trump, Jarvis, & Scarjo’s voice from HER. More in thread 👇

343,045 次观看 • 1 年前

I can't believe this worked! I wanted a modern UI for open-source media tools w/ intelligent workflows & long-form outputs, so I built one. Meet Maestro It automatically generates & edits multishot videos, locally for free. 2 min music video about her love of Grok/xAI😂🎶🔊

I can't believe this worked! I wanted a modern UI for open-source media tools w/ intelligent workflows & long-form outputs, so I built one. Meet Maestro It automatically generates & edits multishot videos, locally for free. 2 min music video about her love of Grok/xAI😂🎶🔊

58,045 次观看 • 3 个月前

Mario irl. Google Veo2 + MMAudio is magic. 🪄😁 (thread 🧵1/3) 🔊🔊

Mario irl. Google Veo2 + MMAudio is magic. 🪄😁 (thread 🧵1/3) 🔊🔊

247,453 次观看 • 1 年前

Here's a cool workflow! I used Perplexity to do Deep Research on how to optimize HGH levels. I put the output into Notebook LM to create a podcast & used Grok to create two podcast persona images. Then, loaded the audio & images into Hedra' new Character 3 model.

Here's a cool workflow! I used Perplexity to do Deep Research on how to optimize HGH levels. I put the output into Notebook LM to create a podcast & used Grok to create two podcast persona images. Then, loaded the audio & images into Hedra' new Character 3 model.

159,041 次观看 • 1 年前

If you really want to get a point across, take the final frame from Pika 1.5 & feed it back in.

If you really want to get a point across, take the final frame from Pika 1.5 & feed it back in.

202,830 次观看 • 1 年前

How to turn yourself into a superhero. Here I am as The Hulk. 🔊🔊 How to; in thread 👇

How to turn yourself into a superhero. Here I am as The Hulk. 🔊🔊 How to; in thread 👇

145,889 次观看 • 1 年前

The Flash forgot to use the bathroom during a joyride. Tools: Real clip of car. Hailuo AI v02 (PSA: star/end Frames are FREE until the 17th)

The Flash forgot to use the bathroom during a joyride. Tools: Real clip of car. Hailuo AI v02 (PSA: star/end Frames are FREE until the 17th)

51,920 次观看 • 8 个月前