This is System Sleep. 🎸 Made with Seedance 2.0 and Kling 3.0. But making this actually started almost 20 years ago

This is Plastic. Made with Veo3. Spoilers in the next post. Watch before reading

This is "Eve & Adam" Tips below on how I made this using Gemini, JSON prompts (and why), Runway Aleph, and Veo3. Spoilers below. Watch before reading 🤘

Hey @McDonalds here's how to make a commercial with AI... Images: @midjourney and @Magnific_AI video: @LumaLabsAI and @runwayml audio: @elevenlabs post production: @Adobe written and edited by: A human (me) #LumaDreamMachine #RunwayGen3 #commercial #McDonalds #AI #GenerativeAI #aivideogenerator #aivideo

Nano Banana was the preview of Google’s new Gemini 2.5 Flash Image model. 🍌 I was given early access on @googleaistudio and created this video based off of 1️⃣ image I was really impressed by how it maintained consistency on the character as well as small details. (Pay attention to his shirt and hat in particular.) 👀 Starting image is in the first comment 👇

Introducing "Mother" An AI horror short using @LumaLabsAI Dream Machine. @udiomusic was used for the music. @elevenlabs + live action for dialogue. @hedra_labs and @D_ID_ were used for lip sync. Images created with @midjourney and @leonardoai Based on a feature script I wrote. Enjoy 🍿 #DreamMachine #horrorai #aivideo #klingai #SoraAI #filmmaking #AIart #GenerativeAI

‼️ Here's how to achieve the most natural-looking Lip Sync in AI videos 👀 I came up with this trick on my latest film Mnemonade, and it gave me great results. Here's how to do it... 🧵👇

This might be the most fun I've ever had creating a video – and it's 100% because of Veo3. Forget fidelity and physics for a second. The real game-changer? Being able to generate dialogue right in the text prompt. What used to take two extra steps now happens instantly — and the quality? Unreal. I started with this simple concept of a plastic kid, but as I kept generating, the story got unexpectedly emotional. I found myself genuinely sympathizing with this character being left out – such a universal feeling. The story could've gone anywhere… What was I trying to say? What was the message? Eventually, I decided: I wanted the process to reflect the joy of creating. I was having too much fun to let it get dark, so I went full meta to pull myself out. The office scenes were pure magic. Those one-liners? First try, usable footage. I literally just typed the dialogue and Veo3 delivered. (Pro tip: text-to-video nails the lip sync, but image-to-video struggles with dialogue – had to use Pixverse for that final conversation scene to keep character consistency.) I was in full stream-of-consciousness mode for the office stuff, not sweating the details. You can tell because nothing in the background matches 😅 For high-stakes work like what we do at @promise_ai (where we're aiming for theatrical release), every detail matters. But for a weekend passion project? This speed + quality combo is unreal. Imagine using this for pre-viz on bigger projects! Just warning – clients might fall in love with the rough cut 😂. You might accidentally make something too good to throw away. Massive respect to the Veo3 team at @GoogleDeepMind Thanks for making tools that help us tell stories — even the ridiculous ones.

Very proud to share my newest film Mnemonade -- which won first prize 🏆 at the Culver Cup competition organized by @AWSstartups and @fbrcai 🎉 More info in the comments. Enjoy 🍿🎥🫶

Veo3 nailed this shot. Working on a scene for an original pilot utilizing json prompts with gemini and veo3. Coming soon. Prompt: { "shot_name": "Aerial Shot (AS) - Car on Dirt Road into Forest", "camera": { "type": "Wide Shot", "movement": "Aerial shot, car turns right off highway onto dirt road, following the car then craning up at the moon in the sky above the forest trees", "lens": "Panavision lenses", "focus": "Car and forest in focus, then car fading", "lighting_direction": "Backlit by evening sky" }, "setting": { "environment": "Highway and a Narrow dirt road leading into dense, overgrown Pacific Northwest forest", "time_of_day": "Night", "atmosphere": "Shifting from isolated to mysterious and ominous" }, "subject": { "main_subject": "Late 1970s muscle car", "details": "Kicking up significant dust, becoming a tiny, fading speck, tail lights receding" }, "visual_style": { "genre": "Action/Sci-Fi Drama", "film_stock": "Kodak 35mm film (Eastman 100T 5247)", "color_grade": "Gritty, natural with deepening purple shadows, cinematic", "rating_tone": "PG-13", "overall_feel": "Cinematic masterpiece" }, "composition": { "elements": "Car swallowed by immense, looming trees; road disappearing into wilderness" }, "implied_elements": { "sound": "Crunch of tires on dirt, rustling leaves, growing silence" } } ]

Since I was a kid, I dreamt of making movies. In the 20 years since film school, I've worked in traditional production as a camera operator, boom mic operator, story producer, screenwriter, actor, and editor. There were times when I felt very close to my dream, and others where I felt hopelessly lost. What I couldn't see then was how this diverse experience was preparing me for something extraordinary. A few years ago, I started a YouTube channel called MetaPuppet to cover VR and metaverse-related content. I had measured expectations and treated it mostly as a hobby. But in September of '22, I discovered Stable Diffusion, and everything changed. In just two short years, the technology matured at an astonishing pace, finally allowing me to bring to life scenes from stories that had lived only in my imagination – stories I'd carried with me for years, now ready to be shared with the world. Today, I'm thrilled to announce that I've taken a full-time role at @promise_ai as Director and Head of Genre. I want to thank industry pioneers @gstrompolos , @jamiebyrne , and @Diesol for not only paving the way forward but for giving me the opportunity to fulfill my lifelong dream of making movies while also helping shape the studio's creative future ✌️

They both need to step down

This is like Runway's Act One on steroids 💉 Of course taking an amazing cinematic performance and transferring it to any AI generated character you want feels dirty, but this is only a research paper to show its capabilities. Link below. X-Portrait 2 highly expressive portrait byteaigc.github.io/X-Portrai…

How I Scored an 8-Minute Film with an 8-Second Veo3 Prompt 🤯 As a traditional editor, one of my least favorite jobs was digging through stock music libraries, hunting for a track that almost fit my scene. It was slow, uninspired, arbitrary, and the result often felt disconnected from my final film… and yet, I did it for over a decade. 🙄 But what if the visuals and the score could share the same creative DNA? 🤔 On my latest Promise short "Eve & Adam," this Veo3 technique saved me hours of searching and gave me a score that feels custom-composed for each scene. Veo3 creates stunning visuals, but it also bakes in sound design, dialogue, and sometimes even music directly into the clips it generates. At first, the unprompted music can be frustrating (music layered over dialogue meant I had to strip the tracks apart with third-party tools). But then I realized: the music was always perfectly tuned to the scene. 💡 - Detectives searching? Tense and mysterious. - Car chase? Thrilling and action-packed. - Spaceship landing? Epic orchestral swells. The challenge? Veo3 clips are capped at 8 seconds. Meaning the music just… stops. So here’s the hack I used to turn that 8-second cue into a full score: 1. Used Gemini to structure my Veo3 music prompt, emphasizing tone and score where needed. Run the prompt in Veo3. 2. Took the 8-second Veo3-generated clip and uploaded it into Suno. 3. Used Suno’s Cover feature + a few descriptive words from my original prompt and remixed the track. The result was a 3-minute cinematic score that not only retained the exact tone of the original 8-second Veo3 output, but expanded on it with remarkable consistency. 🙌 This is an important innovation because shorts made on tight budgets often rely on stock tracks that feel generic or out of sync with the story. With Veo3, the score is generated from the same prompt as the visuals — built from the same creative DNA. The result is a soundtrack inherently tied to the film’s vision, opening up new possibilities for indie filmmakers. ✌️

Here's a Behind the Scenes look at the Coke commercial I worked on with @secret__level 🎥👀

Runway Gen-3 Turbo

Thanks! You guys are doing a great job 👏. Except for the robbery thing I mean

Do you really want your pet to talk? Now that Veo3 image to video with lipsync can make your pets talk, you might not want to hear what they have to say 🐶 The dog’s voice changed with each generation, so until Veo updates with custom voices, you can use the voice changer feature in ElevenLabs on the original Veo3 audio to get consistency.

@TaprootWizards @danheld So many wizards…

This took me 3 weeks to make. My first 100% AI generated film. Love the AI films out there but I wanted something with more of a narrative, so I created "Open Source." I'll be releasing a video on how I made it soon... piped.video/@MetaPuppet Please share and enjoy. Get Everybody Wants to Rule the World by Rebecca Roubion and over 1M + mainstream tracks here go.lickd.co/Music License ID: DzVlMqpRre7 Get Everybody Wants to Rule the World (feat. The Sarm Orchestra and Robbie Williams) by Trevor Horn, The Sarm Orchestra, Robbie Williams and over 1M + mainstream tracks here go.lickd.co/Music License ID: OnQk93EeJdB #aifilms #midjourneyart #PIKALABS #runwayml #AIart #ChatGPT

This video is an example of why I teamed up with @secret__level With them, I got to work with @iamwill on the trailer for the The Black Eyed Peas @bep Las Vegas residency, The 3008 Space Odyssey. It was not only fun to do, it's also the most polished piece I've been a part of. Looking forward to my next project with these amazing artists 🙌 Director: Jason Zada, @jasonzada AI Image Gen: Stephane Benini @BeniniStep9801 Davide Bianca, Aashay Singh @aashay_singh AI Motion / Edit: MetaPuppet @MetaPuppet VFX: Logan McNay @McnayLogan Executive Producer: Monica Monique Producer: Erik Press @expressplay

Let's talk about making this. I used 22 different AI apps over the course of roughly 4-6 weeks, experimenting with each one. I shot live scenes with my wife acting out the part and used style transfer for many of the shots... Then @LumaLabsAI came out with Dream Machine. I fired my wife and re-generated every shot with Luma, so in this case AI did take a job, but she wasn't being paid anyway so we're good 👌 998(ish) generations with Dream Machine brought this to life. @hedra_labs came out while making this which I used for lip sync of the woman. Despite them not having 16x9 aspect ratio, you can do a lot with compositing and putting your character in a doorway. I recorded my daughter's voice and used it for the voice of the little girl. She loved it and it was seriously pretty awesome working with my daughter for the first time 🙌 No I didn't let her watch the whole thing. Hedra flagged the image of the child as underage and wouldn't do the lip sync, so I used @D_ID_ for her. I edited everything in @Adobe Premiere. This is part one of three. In part 2 we go back in time 100 years to see the origin of the witch. Grateful to you for sharing/liking this if you do 🙏

I did this shot by shot, in a linear fashion. I added clips to my timeline in Premiere until the entire story was roughly laid out. On this first pass, the quality of the shots wasn't the priority; I just needed placeholders to begin understanding the film's flow, pacing, and tone. Then I went back to the start of the timeline and regenerated and refined each shot. I did this hundreds of times. I used Runway Aleph to fix inconsistencies in certain shots, as well as change lighting from day to night featuring the same characters. It came out right as I was nearing the end of making this, so I definitely need to spend more time with it, but this kind of natural language in-painting is amazing. Veo3 provides an 8-second clip with sound effects, dialogue, and sometimes even baked-in music. For better sound design and mixing control, we need to export individual stems, so I used Lalal to split the audio. Veo3’s audio often reflects the scene’s tone—for example, tense scenes get tense music—but it cuts off abruptly at the 8-second mark. One trick I used was to upload the 8 second clip’s audio to Suno and use it as inspiration for a longer sound design or music track. This gave me better better audio consistency when cutting between shots in a particular scene. The main theme music is an original song I wrote years ago when I was in a band. I uploaded the recording to Suno and created variations in different styles that serve as Adam's theme song. I love how this tech isn't just helping me visualize new ideas; it's also breathing new life into old ones. I don't think of this as a finished short film, but instead as a starting point. I can pitch this concept to a studio as a TV series or a feature and show this as a teaser. If it gets picked up, we can shoot it for real. This is exactly why this technology needs to be taught in film schools today. Students can pre-visualize their scripts with AI, see what’s working and what isn’t, then shoot it with real actors on set for intimate scenes, while leveraging AI for any big-budget special effects shots. If you're currently in film school and these tools aren't being taught, I have two words for you: Curious Refuge. One question I know I'll be asked is, "How long did this take to make?" The misleading answer is three weeks. But the real answer, as anyone who has worked in production knows, is years. Years of film school and working as an editor on traditional productions cannot be discounted or ignored, because while generative AI excels at creating visuals, it's currently terrible at storytelling. It's not great at writing scripts and definitely can't edit well yet, so those aspects were done traditionally using the skills I learned from a career in post-production. The good news is you don't have to spend years learning every aspect. There are plenty of knowledgeable people in this space looking to connect and collaborate. Team up. Lastly, I don't believe AI cinema will replace traditional cinema; instead, they will co-exist as separate mediums or merge as an evolution of VFX. We’re still going to need actors, writers, editors, and VFX artists, likely even more than before, given the increased demand for productions that these tools will facilitate. Whether it's AI, CGI, live-action film, or theater, at its core, it's all just storytelling. But to me, having this level of visual effects available and affordable is a dream come true. So, experiment, ask questions, and most importantly, have fun! ✌️

🚨 WARNING - Don't watch if you don't want your childhood memories of the Smurfs to be ruined 🤣 I wondered what it would be like if the smurfs were a cult and... things got dark quickly 👀 Enjoy... Sound ON 🔊 Images: @midjourney @freepik @leonardoai Motion: @morphaistudio @leonardoai @HaiperGenAI Narration: @elevenlabs Music: @udiomusic

I remember watching the original "Holidays Are Coming" commercial from Coke when I was a kid and loved it. This year I got asked to work on their new one, using Gen-AI, alongside a great group of people. Thanks @CocaCola and @secret__level for the early Christmas present 🎄🎁 Directed by Davide Bianca and @Diesol CCO: @jasonzada Executive Producer: Monica Monique Motion and Edit: @MetaPuppet Composer and Sound Mixing: Matt Pavolaitis

My thoughts after making this film... As a writer and video editor, I feel that AI filmmaking won’t enter the mainstream until we have emotional dialogue scenes with expressive characters. So I challenged myself with this film to create the most compelling and emotional dialogue scene that anyone has ever seen in an AI film (no big deal 🤷‍♂️). Whether I did or not is subjective. The dialogue scene I’m referring to is toward the end of the film, but I implore you to watch from the beginning. I used @FAL to train a Flux Lora for my main characters, and used Mystic and Flux pro on @freepik for my scenes. I upscaled in @Magnific_AI to get the best possible init images. We were also given a 3D Diner asset made by Global Objects to use in @playbook3d 's new diffusion based engine for 3D scenes. Then I performed the dialogue parts. I sat there at my computer, performing take after take using @elevenlabs speech to speech tool, fake sobbing and moaning and breathing like an idiot, really selling it lol… then I used a combination of @lipdubai and @Kling_ai 's lip sync tool, plus some editing tricks to make the lip sync very smooth and natural. But the tools to achieve realistic lip-sync are only half the battle. Good dialogue scenes are hard to do, and it can take years to hone the craft of advancing a story in an entertaining way. This led me to the conclusion that there are 3 paths for #AIfilmmaking in the near future… Path 1: People will try making #aifilm , realize filmmaking is hard and either just make little things for fun or give up on it altogether. Path 2: People will keep going and actually learn filmmaking. This will take time, but AI workflows will be incorporated in film school programs and taught in online courses. PATH 3: People will hire skilled professionals. It’s my belief that we will need more #VFX artists, editors and writers, not less, due to the explosion of content that’s coming. Currently when I work with my commercial agency @secret__level on a project, we use multiple VFX artists. If you are a VFX artist and you align yourself with the AI community, I think you can work everyday if you want to. As for the inspiration for the film… my grandmother Judy passed away about one year ago at the age of 93, and she had dementia. Her husband, my grandfather, passed away in the 1980s. I visited her last year in the assisted living home she was in and watched as she experienced vivid hallucinations from her past. I thought that maybe I captured a little bit of what it was like for her in the flashback scenes in Mnemonade. My film debuted at the Culver Cup competition organized by @fbrcai and @AWSstartups . 50 filmmakers, of which I was one, were given a creative treatment crafted by @DAVID_A_SLADE and we had 3 weeks to go from idea conception to finished video. 8 of us were selected as finalists, and I’m honored to say that Mnemonade was chosen as the winning film. Guillermo del Toro @RealGDT recently claimed that AI-generated films couldn't evoke deep emotions by stating, "Are they going to make them cry because they lost a son? A mother? F*** no!" Several people came up to me after my film was shown and told me how they lost a loved one to dementia and that the film made them cry. I’m a fan of Guillermo’s work, but the reason why he made that quote about AI film is because he just hasn’t seen the proof yet. In the past 2 years of AI video’s infancy, the tech has outshined the story. That’s on me, and creators like myself, who have come from traditional filmmaking backgrounds and embraced AI, but have not used it to its full potential. As early as we may be, it’s our job to create content where the story speaks louder than the tools used to tell it. My hope is that Guillermo and others see work like this and realize its potential. The #Filmmaking pipeline in #Hollywood is too small for today’s technology, and it’s about to get a lot bigger. Companies and platforms are stepping up to provide the tools needed to lift new voices and stories up out of obscurity. If you want to be one of those voices, the biggest thing you can do to help yourself is to learn the fundamentals of filmmaking. AI tools change frequently, but the fundamentals of storytelling do not. Social media feedback is not always the most constructive, but there are a lot of people in this community who will help and I hope to be one of them. So get started and have fun. To quote Rob Schneider from the movie Waterboy, “You can do it!” 🫶

Is your video in this mashup? 👀 The best part about being asked to edit this for Escape was that I got to watch and re-watch my fellow creators content from 2024. While editing it I was struck with gratitude for somehow being a part of the community who will forever be known as the first to tell stories with this new tech… not for money, just for passion. Happy new year guys. 2025 is going to be even better 🫶

Easter eggs in your videos are the new watermark. Veo3 makes it easy. Did you catch it?👇

Here's Carmen from my film Mother accepting her "Best Actress" award during the AI International Film Festival 🎞️ She may be an AI actress created with @hedra_labs new 1.5 model, but she's still a diva 👩‍🎤 Mother won 3 awards this night, thanks to the festival organizers and everyone who voted 🏆🏆🏆 #Oscars #aivideo #ainews

This project marked my first experience with JSON prompting. While I skipped the social media debate about whether JSON prompting gives better results —after three years of crafting natural language prompts in paragraph form, the structure this format provided simply made sense to my brain. First, I described the shot I wanted to create to Gemini, which then gave me a prompt in JSON format that I would feed into Veo3. I'd run an initial generation without even reading the prompt, just to see the output. Once I saw how far off the initial generation was from my vision, I'd then read the prompt and find the exact category I needed to tweak—be it lighting, composition, or the subject itself—thanks to the prompt's structured format. To me, this was far easier than revising a block of natural language text. Another advantage: I could copy and paste the entire JSON prompt into Veo3 due to its large token limit, whereas other platforms would hit their character count maximum. Example prompt: { "shot_name": "Aerial Shot (AS) - Car on Dirt Road into Forest", "camera": { "type": "Wide Shot", "movement": "Aerial shot, car turns right off highway onto dirt road, following the car then craning up at the moon in the sky above the forest trees", "lens": "Panavision lenses", "focus": "Car and forest in focus, then car fading", "lighting_direction": "Backlit by evening sky" }, "setting": { "environment": "Highway and a Narrow dirt road leading into dense, overgrown Pacific Northwest forest", "time_of_day": "Night", "atmosphere": "Shifting from isolated to mysterious and ominous" }, "subject": { "main_subject": "Late 1970s muscle car", "details": "Kicking up significant dust, becoming a tiny, fading speck, tail lights receding" }, "visual_style": { "genre": "Action/Sci-Fi Drama", "film_stock": "Kodak 35mm film (Eastman 100T 5247)", "color_grade": "Gritty, natural with deepening purple shadows, cinematic", "rating_tone": "PG-13", "overall_feel": "Cinematic masterpiece" }, "composition": { "elements": "Car swallowed by immense, looming trees; road disappearing into wilderness" }, "implied_elements": { "sound": "Crunch of tires on dirt, rustling leaves, growing silence" } } ]

Kling's new Elements feature is a BEAST 👏 Upload up to 4 images as Elements and prompt your scene. Impressive results 📷👀

This is the initial image I started with. Then, using Nano Banana, I prompted for him to be in several different situations. I used Veo3 on Flow for motion. Thanks Google for the early access!

Got to collab with my man Dave Clark on a Veo 2 video this weekend 🙌 So much fun!

I had such a great time last night at the Culver Cup competition where I got to meet so many of my AI friends IRL. THANK YOU to the organizers and congratulations to all the finalists! And THANK YOU to everyone who came! It was a full house and as promised here’s the picture I took of all of YOU from the stage. Tag anyone I missed! I can’t post my winning film here yet, but hopefully very soon! 🫶 @fbrcai @LumaLabsAI @secret__level @playbook3d @elevenlabs @Diesol @MaxEinhorn @NemPerez @D_Ryan_Reeb @glamoureptile @theescapeai @DAVID_A_SLADE @ToddTerrazas @AWSstartups @netflix @CuriousRefuge #LATechWeek #aifilmmaking #culvercup

This is one of the tricks I used on my film Mnemonade which won the Culver Cup competition organized by @AWSstartups and @fbrcai If you haven't seen it yet here it is...

Tools used: Gemini, Veo3, Freepik, Runway, Magnific, Midjourney, ElevenLabs, Suno, Kling, Hailuo, Dreamina, Luma, Topaz

Sneak peek of some of the work we’re doing at Promise!

I used @Kling_ai to generate a shot of my character performing the emotion that I wanted. Kling's v1.5 model has the highest visual fidelity imo. When you're happy with your shot, press the "Lip Sync" button below your video. Make sure your character's face remains on the screen the whole time in good lighting, otherwise Lip Sync might fail. After it successfully detects your character's face, you can create speech using text and one of their pre-trained voices, or you can upload your own recording, which is what I did.

Episode 2 of Before They Were Famous! starring He-Man and Skeletor... now with a laugh track!!

I'm honored that my film "Mnemonade" is an official selection of this year's Beverly Hills Film Festival 🎥🏆 and will be screened at the TCL Chinese Theatre in Hollywood on Wednesday, April 3rd 🍿 What makes this even more special is that the BHFF is not an AI film festival, but a traditional film festival that is considered among the most exclusive and influential film festivals globally. To have such a prestigious festival — located in the heart of Hollywood — choose a film made with generative AI as an official selection represents a new level of acceptance that I'm so happy to see. I applaud the BHFF for judging my film based on its story, not on how it was made. 🫶

Link to 4K video on Youtube: piped.video/gePD1Hf1qPc

Eve and Adam is a story about a brother and sister who are part human, part machine—the first of what could be the next evolution of the human species. It all started with an idea of someone shooting at the moon. I asked myself, why would anyone do that? Each answer led to another question, and the story of "Eve and Adam" began to unfold. I wanted to capture the nostalgia of films like Close Encounters of the Third Kind and Escape to Witch Mountain, so I used Gemini to research the equipment those films were shot on and to help craft prompts that would maintain that classic look. I used Veo3 text-to-video and image-to-video for the visuals.

Thrilled to publicly announce that I’ve signed with @secret__level for commercial representation 🙌 They rep some of the biggest AI creators and work with some of the largest brands to bring next-gen entertainment to the masses. Excited to learn from and grow with this roster of talented professionals 🫶🎉 #Advertising #commercial #agency #ai

👀FINALLY I can share that my film Mnemonade -- which won this year’s Culver Cup competition organized by @AWSstartups and @fbrcai -- will premiere this Monday, October 28th at 12pm PDT, followed by a live Q&A with myself and @jasonzada from @secret__level I hope to see you there to watch the film and talk about the future of storytelling and AI 🍿🎉🎥 Click the link in the comments and sign up! #aivideo #storytelling #aifilm

Anyone else wish this was real? Deepfakes don't always have to be negative. Bring America Together Again 🫶 #BATA #Debate2024 #KamalaHarris #TrumpHarrisDebate

Well, Apple finally did it... Sentient Siri Here's a first look at the iPhone update that nobody wants 😱 🤣

Have you heard about Image 2 World? 🌎 Explorer by @odysseyml is a generative image-to-world model that transforms any image into a realized, detailed 3D world 👀 Crafting detailed worlds with traditional 3D tools is a time-consuming process which is a bottleneck for film, gaming, and more. Explorer offers the promise to significantly accelerate the creation of film and gaming-compatible worlds. More examples with prompts below 👇

🫧 Ethereal Bubbles 🫧 Images and upscale: @leonardoai Motion: @leonardoai , @runwayml , @morphaistudio , @HaiperGenAI Music: @suno_ai_ Edited in @Adobe Premiere Pro Have a light day 😎

Episode 3 of Before They Were Famous: starring Adam & Keldor is out now! In this episode we meet Evil-Lyn Before They Were Famous is the first AI-generated episodic series. Images made with: @freepik @leonardoai @midjourney Animation: @leonardoai @morphaistudio Lip sync: @runwayml @pika_labs @D_ID_ Music: @udiomusic

Hahaha love it man. “Hang in there” 👏😂

DCA and don’t worry about it

BIG THANKS to @fbrcai and @AWSstartups for selecting me to participate in the Culver Cup! 🎉 Only 50 creators were selected so this is a HUGE honor 🙏 Congrats to the other participants! Looking forward to raising the bar of #aivideo together 🙌

Kling v1.5

Now that the full film is out and can be watched on @RadNFTV , I'm sharing my scene for the @t2remake that I did 6 months ago. @NemPerez and @SwayMolina produced the project, and I'm now part of an awesome community of AI artists because of it. This cast of characters could only be assembled in one scene by AI, the budget would've been too big otherwise 🤣 Tools used were @midjourney for the images, @KaiberAI and @runwayml and @pika_labs for the video, @elevenlabs for the voices

I used this as the starting image for the shirt coming out of the bag

What an honor it is to work with the one and only Dave Clark 🙌

I’m appalled to learn that “camera tricks” and “special effects” have been used in movies for almost a century. I had assumed that everything I have ever watched was practical. Now hearing reports that The Martian was shot in a desert and not on Mars. And no one is talking about it! I have never watched end credits in my life and never bothered to learn how the whole process works but I just know it must stop. I am boycotting movies and Matt Damon and am sticking to Facebook where I know things are real 🤦‍♂️

Haiper 2.5

It’s almost like they’re afraid of losing control over the world economy or something 🤷‍♂️

To be that triggered and angry to the point where he can’t regulate his emotions and lashes out like a child points to a deeper problem for that individual. We can all co-exist online with compassion, just chill ✌️

Watch the 4K version here: piped.video/_tIm8GBKRJ0

We’re building web3 and the government’s web2 still doesn’t work

In #McDonalds terms, this cost less than 60 happy meals to make 🍔

If you appreciated this tip, please like and repost the first post. Thanks and good luck!!

Luma. No prompt, 1 iteration

Proud to be listed among these respected creators 🙌

@UnbankedHQ Banker NFTs featured in this video at 3:50... piped.video/R4Hp4x6CzfA

In @runwayml , scroll down until you find "Super-Slow Motion" and click the tab. Upload your lip synced video from @Kling_ai and process it at .5 speed. Your clip will now be half speed. You've now added frames to your original video.

The video Kling returned is pretty good out of the box, but you can see how it's a little choppy. I believe this is due to the frame rate being lower than the original video. But here's a trick you can do to smooth it out. Head over to @runwayml ... 👀

I’ve used @elevenlabs for every single one of my AI films. I don’t know how I would do it without them. It’s incredibly powerful and I feel like sometimes they go under the radar. Just want to show them some love ❤️ And, they just released something new, Iconic Voices. 👏 Check it out 👇

Gliding to a city near you! 🦸‍♂️🤙

The real reason Rose didn't let Jack on that door when the Titanic sank @runwayml @pika_labs @leonardoai

Yes it does… 👇 “This feels like indie filmmaking again—except with better tools and more ownership.” @gstrompolos forbes.com/sites/charliefink…

Quick way to stay objective when making an AI film… 1. Watch it back and pretend you didn’t make it. This helps remove your ego and typically you’ll give a more honest critique when the work is not your own. 2. Pretend it’s not AI We’re amazed by the tech, but if you show your film to people who are not in the AI bubble like we are, they will not be impressed by the visuals, in fact they’ll think it looks bad. That’s because their frame of reference are big budget films with traditional VFX, which are great (usually). They won’t care about how many generations it took to get that shot, just like they don’t care about how many hours the rotoscoping took in a traditional VFX film. Only one thing will determine whether they like your film or not, and that’s number 3… 3. Is the story good? I’m blown away by the tech too. But all shiny toys fade and we will soon be numb to the “I can’t believe this is AI” refrain. After that, all that’s left is the story. Is every shot serving your story in some way? Or is it in there just because it’s pretty, or because it took 100 generations to get that movement? If it’s not providing information that is moving the plot forward, you should probably lose it. All of this comes from traditional filmmaking. For me the only difference in making film with AI vs live action is that the footage was generated as opposed to coming to me on a hard drive from a production team. After that the post production process is pretty much the same and all traditional rules apply. Study traditional filmmaking. If you have any favorite books on writing and storytelling for film, drop them below 👇 ✌️

I'm honored to have been selected as a finalist in the Culver Cup competition 🙏🎉 organized by @fbrcai and @AWSstartups I'll be in LA on Monday (Oct 14th) to attend the event at the Culver theater where my film Mnemonade will be screened along with 7 other films from very talented creators. If any of you are in LA, RSVP for the event, watch some groundbreaking films and let's meet up. After-party at Culver Hotel across the street. If you're not in the area I'll be releasing my film on socials next week! 🫶 #latechweek #culvercup

If your audio is longer than 5 seconds, you'll have to crop your audio clip. Trim your audio, then click the Lip Sync button and wait for your lip sync video to generate.

Shout out to @minchoi for including my short film “Mother” in the list along with these other incredible AI films!

Yes, Celsius will cover the money you lost on your house 👍

I'm proud to be a small part of this AI community. Happy holidays to all of you. This year was groundbreaking. I can only imagine what amazing works of art next year will bring 👏 @MaxEinhorn @NemPerez @javilopen @SwayMolina @pressmanc @DaveJWVillalva @TheStithLord @MatanCohenGrumi @CitizenPlain @JohnMeta8 @LinusEkenstam @Uncanny_Harry @AIandDesign @bennash @alexutopia @The_Ai_Daddy @Cinemai_tv @The_DailyAi @runwayml @CuriousRefuge @pika_labs @elevenlabs @midjourney @JeffSynthesized @TheoMediaAI @AIAnimationCom

Thanks man! Took a weekend. Veo3 is unreal!

This is the best I’ve seen yet

Vidu 1.5

Once the clip is synced, delete the sped up (high-pitched) audio. Your lip sync clip will now be the same length as the original, but due to the added frames we created, the mouth movement will be a lot smoother.

Imagine developing a new concept every other week 😯 That's what my co-worker and Promise co-founder @Diesol does and he just dropped a new one. Check it out 👇

Hi Kiri, I’m interested. Thanks for sharing!

My horror short film “Mother” is in Forbes this week! Big thanks to @CharlieFink for the write up 🙌

You guys may know me for my posts about AI, but as a video editor in the docu-style space, I'm incredibly proud to share that my team just won an Emmy for a piece I edited and co-story produced about disabilities in the workforce! It's so rewarding to be part of a team that puts meaningful content out into the world. Congrats to my fellow colleagues! 👏👏👏

A Nazgul posing for a photo shoot. He's missing his right hand so the photographer is holding his glass of wine for him. First time generating with @HotshotSupport , a new AI video generator, impressed by the movement and realism, definitely going to be doing more with them 🙌 #aivideo #aitools

Leonardo

If you've ever heard about AI tools like ComfyAI, automatic 1111, AnimateDiff or OpenPose but you aren't techy and Github is scary... try Pinokio's web browser. It's a convenient interface that lets you install and run these AI apps and more right from your desktop without the techy stuff that can be intimidating. I use it to test out different methods when starting an AI video project. Check it out! pinokio.computer

Import the clip into your editor of choice. For this project I used @Adobe Premiere Pro. Drag your super slo-mo clip into the timeline and changed the speed of the clip to 200. Then use the audio waveforms to sync your clip to the original one in the timeline.

Export your video clip at the highest format and resolution available to you. For mine, I used ProRes at 1080p. MAKE SURE YOU INCLUDE AUDIO. This will help when you're syncing your clip in your timeline. Click Export.

Who do you think they’ll get to play Sam in the movie?

Images made with @freepik and @midjourney Upscaled with @leonardoai Motion: Leonardo, @morphaistudio , @HaiperGenAI Lip sync: @runwayml and @pika_labs Music: @udiomusic

Music by @suno_ai_ and @udiomusic

The Promise family just got bigger 🙌

Please vote for our panel at SXSW, "The Secret Sauce of AI Filmmaking in Advertising", featuring @Diesol, @MetaPuppet , and @jasonzada - moderated by Monica Monique. Only a few days are left, so help us rock Austin with some AI filmmaking knowledge! panelpicker.sxsw.com/vote/15… #SXSW2025 #aifilm

Remember the arcades? Arcade galaxy is bringing it to the blockchain... piped.video/watch?v=3xvERuaL…

🚨Fellow AI peeps… Hollywood is taking notice! 👀🤘🎉

This makes me want to do animation