Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Mini tutorial for Google DeepMind 's VEO 2 Prompt Buddy. (Works well with other AI video tools as well). I’ve created my VEO 2 Prompt Buddy Custom GPT to help me go beyond my own brain and prompts. It can describe your images, enhance your prompts, be creative and...

AllarHaltsonen's profile picture

Allar Haltsonen

14,709 subscribers

58,509 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Allar Haltsonen
Allar Haltsonenvor 1 Jahr

Veo 2 Prompt Buddy

Profilbild von Yang
Yangvor 1 Jahr

Build powerful AI agents and automations for your business today. Check out our step-by-step video tutorials 100% FREE 🥳

Profilbild von LongLimbsLenore
LongLimbsLenorevor 1 Jahr

@GoogleDeepMind So much effort just to be an unethical poser

Profilbild von TomLikesRobots🤖
TomLikesRobots🤖vor 1 Jahr

@GoogleDeepMind Cool. I'll give this a go. I've been using Sora Storyboard to caption images and expand prompts. I'd planned on putting together a Custom GPT but didn't around to it.

Profilbild von Allar Haltsonen
Allar Haltsonenvor 1 Jahr

@GoogleDeepMind Sounds good! Thanks man!

Profilbild von Farhan
Farhanvor 1 Jahr

@GoogleDeepMind Gonna try this bro. Thank you

Profilbild von Allar Haltsonen
Allar Haltsonenvor 1 Jahr

@GoogleDeepMind Your welcome bro!!

Profilbild von James D Phillips 2
James D Phillips 2vor 1 Jahr

@GoogleDeepMind Incredible, Allar. Thanks so much. I'm in! 🔥🧯🚒🔥

Profilbild von Allar Haltsonen
Allar Haltsonenvor 1 Jahr

@GoogleDeepMind Let’s go man! Let me know how it goes 🔥🙏🏼

Profilbild von Brent Lynch
Brent Lynchvor 1 Jahr

It did a great job, for Minimax on this. I try out all the prompt helpers and this blew most of them out of the water and is right up there Google VEO2 however refused to generate this prompt. You may want it to review prompt for compatibility with VEO2 standards (which I admit are hard to pin down) but allow flexibility to keep as or tone down as needed. I would say my other note is if you ask it to generate a series of shots, it won't describe the character again, so possibly if you could tweak it to always include the character descriptions. Prompt: Character Description: The assassin is a striking woman in her late 20s, with piercing green eyes, a chiseled jawline, and lips painted a deep crimson. Her dark, form-fitting tactical suit is adorned with hidden holsters, ammo clips, and sleek combat boots that barely make a sound against the metal floor. A long, black coat trails behind her, tattered at the edges from past battles. Her hair, a wild cascade of golden waves, bounces with each determined step. 🔹 Scene & Motion: [Tracking shot,Shake]The long, sterile hallway is bathed in flickering fluorescent light, red alarm sirens pulsing against the walls. Smoke billows from distant gunfire, and the camera starts at a low angle, tracking backward in slow motion as she sprints toward the lens, twin pistols in hand. Her breath is steady, her expression unreadable—this is a woman who never misses.

Profilbild von Allar Haltsonen
Allar Haltsonenvor 1 Jahr

@GoogleDeepMind Noted, thanks a lot!

Ähnliche Videos

Create custom footage from a prompt using Google Vids with Veo 3. In this tutorial, we’ll walk you through creating 8-second AI video clips with sound, plus tips for writing effective and detailed prompts. Watch now. →
3:22

Create custom footage from a prompt using Google Vids with Veo 3. In this tutorial, we’ll walk you through creating 8-second AI video clips with sound, plus tips for writing effective and detailed prompts. Watch now. →

Google Workspace

18,486 Aufrufe • vor 9 Monaten

Video Model Comparison: Image to video I updated an older comparison with a new image and prompt to test in several models: • Pika 2.2 • PixVerse 4 • Runway Gen-4 • Google Veo 3 • OpenAI Sora • Kling 2.1 Pro • Luma Ray2 • Hailuo I2V I used the same prompt and Midjourney image in each model 2-3 times and chose my favorite results below:
1:12

Video Model Comparison: Image to video I updated an older comparison with a new image and prompt to test in several models: • Pika 2.2 • PixVerse 4 • Runway Gen-4 • Google Veo 3 • OpenAI Sora • Kling 2.1 Pro • Luma Ray2 • Hailuo I2V I used the same prompt and Midjourney image in each model 2-3 times and chose my favorite results below:

Heather Cooper

98,259 Aufrufe • vor 1 Jahr

Google Veo 3 is fantastic at understanding prompts and camera movements. In this video I tested some longer prompts that involve the camera moving from one place to another. Check this out.
1:28

Google Veo 3 is fantastic at understanding prompts and camera movements. In this video I tested some longer prompts that involve the camera moving from one place to another. Check this out.

Jerrod Lew

39,904 Aufrufe • vor 1 Jahr

This custom GPT writes perfect Sora 2 prompts every time 🤯 Most people are wasting hours trying to get Sora 2 to generate decent UGC videos. The problem isn't Sora 2. It's you (and your prompts). Here's what I learned after generating 100+ UGC videos with Sora 2: Sora 2 needs hyper-specific prompts with shot composition, timing, camera movement, and scene details. Most people write: "Create a UGC video for my protein bar" What you get? Terrible results. What actually works: "9:16 vertical handheld shot, natural lighting, female creator in kitchen holding [brand] protein bar at eye level, excited testimonial energy, 0-3s hook showing bite and reaction, shallow depth of field, warm color grade" That's the difference between amateur & professional output. So I built a custom GPT that does this automatically: → Tell it your product (protein bar, skincare, SaaS tool, etc.) → It generates a detailed timeline-based Sora 2 prompt → Includes shot composition, camera angles, timing breakdowns → Optimized for 9:16 UGC TikTok/Reels format → Copy/paste directly into Sora 2 No more guessing. No more mediocre results. Just professional UGC prompts in 10 seconds. Want free access to the Sora 2 Prompt Generator GPT? > Comment "GPT" > Like this post And I'll send it over (must be following so I can DM)
0:23

This custom GPT writes perfect Sora 2 prompts every time 🤯 Most people are wasting hours trying to get Sora 2 to generate decent UGC videos. The problem isn't Sora 2. It's you (and your prompts). Here's what I learned after generating 100+ UGC videos with Sora 2: Sora 2 needs hyper-specific prompts with shot composition, timing, camera movement, and scene details. Most people write: "Create a UGC video for my protein bar" What you get? Terrible results. What actually works: "9:16 vertical handheld shot, natural lighting, female creator in kitchen holding [brand] protein bar at eye level, excited testimonial energy, 0-3s hook showing bite and reaction, shallow depth of field, warm color grade" That's the difference between amateur & professional output. So I built a custom GPT that does this automatically: → Tell it your product (protein bar, skincare, SaaS tool, etc.) → It generates a detailed timeline-based Sora 2 prompt → Includes shot composition, camera angles, timing breakdowns → Optimized for 9:16 UGC TikTok/Reels format → Copy/paste directly into Sora 2 No more guessing. No more mediocre results. Just professional UGC prompts in 10 seconds. Want free access to the Sora 2 Prompt Generator GPT? > Comment "GPT" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

49,645 Aufrufe • vor 8 Monaten

🎨 GOOGLE VEO 2 PROMPTS THREAD🎨 Google VEO 2 has been added yesterday to Freepik AI Suite and the possibilities are insane. Here for you some prompts for Google VEO 2 , more about VFX than realistic You can use them as ideas or base prompts. All details in thread ( prompts and videos) , bookmark for later👇 1/15
1:15

🎨 GOOGLE VEO 2 PROMPTS THREAD🎨 Google VEO 2 has been added yesterday to Freepik AI Suite and the possibilities are insane. Here for you some prompts for Google VEO 2 , more about VFX than realistic You can use them as ideas or base prompts. All details in thread ( prompts and videos) , bookmark for later👇 1/15

LudovicCreator

23,584 Aufrufe • vor 1 Jahr

Watch my latest animated AI short, "The Greyhound." This was created entirely with Google Veo 2 text to image to video. The world is now your creative playground. I made this in collaboration with my good friend MetaPuppet What story will you tell next? Google DeepMind Google Labs
2:20

Watch my latest animated AI short, "The Greyhound." This was created entirely with Google Veo 2 text to image to video. The world is now your creative playground. I made this in collaboration with my good friend MetaPuppet What story will you tell next? Google DeepMind Google Labs

Dave Clark

17,379 Aufrufe • vor 1 Jahr

Now on Poe: Veo 2! Widely regarded as the world’s leading video generation model, Veo 2 generates stunning, realistic video from text prompts in a wide range of styles - and Poe is one of the only places you can use it! (1/2)
0:20

Now on Poe: Veo 2! Widely regarded as the world’s leading video generation model, Veo 2 generates stunning, realistic video from text prompts in a wide range of styles - and Poe is one of the only places you can use it! (1/2)

Poe

27,923 Aufrufe • vor 1 Jahr

Seems like Google Veo 2 is really good at this kind of thing. I tested it alongside Kling 2.0 and Luma Ray 2. All are great, but somehow I prefer Veo 2's output. It feels more natural, I guess. This one was inspired by some of my favorite DJ set channels on YouTube, such as bbyb radio, PAN!C ROOM, and SENJO. It’s a mostly fixed-camera DJ set. Image-to-Video Prompt: [Static/Handheld] camera, [subject] adjusts the knobs and taps the mixer with calm focus, candid and natural head sway and hand motion. → text2img: MidJourney v7 → img2vid: Google Veo 2 via Freepik → music: Udio
0:27

Seems like Google Veo 2 is really good at this kind of thing. I tested it alongside Kling 2.0 and Luma Ray 2. All are great, but somehow I prefer Veo 2's output. It feels more natural, I guess. This one was inspired by some of my favorite DJ set channels on YouTube, such as bbyb radio, PAN!C ROOM, and SENJO. It’s a mostly fixed-camera DJ set. Image-to-Video Prompt: [Static/Handheld] camera, [subject] adjusts the knobs and taps the mixer with calm focus, candid and natural head sway and hand motion. → text2img: MidJourney v7 → img2vid: Google Veo 2 via Freepik → music: Udio

Dan Pradana

18,772 Aufrufe • vor 1 Jahr

EXPERIMENT: VFX + Camera Transitions in Veo 3 I've been playing with VEO 3, trying out some cool VFX and camera transitions with simple prompts. Check out these 6 examples (plus all the prompts) ... 👇
0:41

EXPERIMENT: VFX + Camera Transitions in Veo 3 I've been playing with VEO 3, trying out some cool VFX and camera transitions with simple prompts. Check out these 6 examples (plus all the prompts) ... 👇

Marco

66,980 Aufrufe • vor 10 Monaten

Auto movie generation with Veo-2! 🤯 I wrote a python script which creates whole short movies using Veo-2 API, Link to code in comment "a macro camera documentary in backyard grass" 1- it generates scene descriptions automatically 2- then generates the video in parallel using Veo-2 3- then combines them You can download the code by joining my AI community
0:20

Auto movie generation with Veo-2! 🤯 I wrote a python script which creates whole short movies using Veo-2 API, Link to code in comment "a macro camera documentary in backyard grass" 1- it generates scene descriptions automatically 2- then generates the video in parallel using Veo-2 3- then combines them You can download the code by joining my AI community

echo.hive

11,045 Aufrufe • vor 1 Jahr

Grok is a sleeping giant for AI animation Tested the collage hack from - upload one image of your characters + environment + a prompt The results are MIGHTY impressive Also ran the same prompts in Veo 3.1 and the differences are surprising Results + prompts below 👇
0:33

Grok is a sleeping giant for AI animation Tested the collage hack from - upload one image of your characters + environment + a prompt The results are MIGHTY impressive Also ran the same prompts in Veo 3.1 and the differences are surprising Results + prompts below 👇

Billy Woodward

36,193 Aufrufe • vor 8 Monaten

Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):
0:41

Google just released Veo 2, a new state-of-the-art AI video model. In testing, Veo beat OpenAI Sora in BOTH quality and prompt adherence. The video compilation below is 100% created by AI (more details in thread):

Rowan Cheung

249,907 Aufrufe • vor 1 Jahr

🎬 Want to create cinematic AI videos in seconds? Here’s exactly how I do it using Seedance 2.0 on Yapper: Most people get this wrong… your results depend on how well you *direct* the AI. Here’s the workflow 👇 ✅ Step 1: Open Yapper Go to Create → Video ✅ Step 2: Choose your model Select Seedance 2.0 This model delivers smooth motion, dynamic camera angles, realistic lighting, and strong scene consistency. ✅ Step 3: Write a strong prompt Your prompt is your director. Be specific: Camera movement (pan, zoom, tracking shot) Lighting (golden hour, neon, soft shadows) Environment (city, desert, luxury interior) ✅ Step 4: Add a reference image (optional) Use this to guide style, composition, or subject for more control and consistency. ✅ Step 5: Hit Generate In seconds, your idea turns into a cinematic sequence. 🚀 Pro tip: If it’s not perfect, tweak your prompt — small changes = big difference. From idea → cinematic video in seconds.
1:00

🎬 Want to create cinematic AI videos in seconds? Here’s exactly how I do it using Seedance 2.0 on Yapper: Most people get this wrong… your results depend on how well you *direct* the AI. Here’s the workflow 👇 ✅ Step 1: Open Yapper Go to Create → Video ✅ Step 2: Choose your model Select Seedance 2.0 This model delivers smooth motion, dynamic camera angles, realistic lighting, and strong scene consistency. ✅ Step 3: Write a strong prompt Your prompt is your director. Be specific: Camera movement (pan, zoom, tracking shot) Lighting (golden hour, neon, soft shadows) Environment (city, desert, luxury interior) ✅ Step 4: Add a reference image (optional) Use this to guide style, composition, or subject for more control and consistency. ✅ Step 5: Hit Generate In seconds, your idea turns into a cinematic sequence. 🚀 Pro tip: If it’s not perfect, tweak your prompt — small changes = big difference. From idea → cinematic video in seconds.

Kuria | AI

43,685 Aufrufe • vor 1 Monat

Watch one of our favorite Veo 3.1 features in action ⬇️ With Veo 3.1, you can quickly and easily make creative videos in the Google Gemini and Google Flow based on just ingredient images and a prompt. It’s designed to give you more creative control while generating mobile-first videos. Have you tried Veo 3.1 yet?
0:25

Watch one of our favorite Veo 3.1 features in action ⬇️ With Veo 3.1, you can quickly and easily make creative videos in the Google Gemini and Google Flow based on just ingredient images and a prompt. It’s designed to give you more creative control while generating mobile-first videos. Have you tried Veo 3.1 yet?

Google

59,005 Aufrufe • vor 2 Monaten

VEO 3 + Markdown prompting is pretty wild 🤯 This BRĒZ UGC video was created entirely with AI. And it's all about the prompt. This Markdown prompting technique will take any generic VEO3 prompt.. And turn it into surgical-precision video generation with brand consistency. Perfect for creative strategists and DTC operators. But instead of manually writing paragraph prompts and hoping for good outputs... Just use structured Markdown prompts and get brand-ready videos with way higher coherence. The best part? Your prompt precision goes through the roof -> organized by camera angles, brand elements, lighting specs, & scene transitions. Here's what Markdown prompting gives you: → hierarchical structure instead of paragraph descriptions → precise creative direction for VEO 3 → consistent brand-ready video outputs → way higher prompt coherence → eliminates the creative lottery problem Now you've got predictable video generation instead of random outputs. Want the full Markdown prompt templates? Comment "MARKDOWN" + like and I'll send it over (must be following so I can DM)
0:23

VEO 3 + Markdown prompting is pretty wild 🤯 This BRĒZ UGC video was created entirely with AI. And it's all about the prompt. This Markdown prompting technique will take any generic VEO3 prompt.. And turn it into surgical-precision video generation with brand consistency. Perfect for creative strategists and DTC operators. But instead of manually writing paragraph prompts and hoping for good outputs... Just use structured Markdown prompts and get brand-ready videos with way higher coherence. The best part? Your prompt precision goes through the roof -> organized by camera angles, brand elements, lighting specs, & scene transitions. Here's what Markdown prompting gives you: → hierarchical structure instead of paragraph descriptions → precise creative direction for VEO 3 → consistent brand-ready video outputs → way higher prompt coherence → eliminates the creative lottery problem Now you've got predictable video generation instead of random outputs. Want the full Markdown prompt templates? Comment "MARKDOWN" + like and I'll send it over (must be following so I can DM)

Mike Futia

38,280 Aufrufe • vor 8 Monaten

The Cleaner. Made with Veo 3. I wanted to challenge myself this past weekend and string an actual narrative together using all the capabilities of Google Flow and Veo 3. Veo 3 works exceptionally well when you know what to prompt for and have a story to tell. Consistency is something we can strive for now. Sure, a few minor details like gloves, etc, change. But I believe we are at the inflection point where we can finally tweak those things. This was 100% text-to-video using detailed prompts. I do a few prompt shares with screenshots in the comments. Exciting times.
3:13

The Cleaner. Made with Veo 3. I wanted to challenge myself this past weekend and string an actual narrative together using all the capabilities of Google Flow and Veo 3. Veo 3 works exceptionally well when you know what to prompt for and have a story to tell. Consistency is something we can strive for now. Sure, a few minor details like gloves, etc, change. But I believe we are at the inflection point where we can finally tweak those things. This was 100% text-to-video using detailed prompts. I do a few prompt shares with screenshots in the comments. Exciting times.

Dave Clark

121,378 Aufrufe • vor 1 Jahr

This custom GPT writes Sora 2 prompts that actually work 🤯 Most people prompting Sora 2 are getting garbage output. The problem isn't Sora 2. It's your prompts. Here's what I figured out after generating 100+ UGC videos: Sora 2 needs hyper-specific instructions—shot composition, timing, camera movement, lighting, scene details. Most people prompt like this: "Make a UGC video of someone using my skincare product" And then wonder why the output looks like AI slop. What actually gets results: "9:16 vertical handheld shot, soft natural window lighting, female creator mid-20s in bathroom mirror holding [brand] serum at eye level, genuine testimonial energy, 0-3s hook showing application and subtle reaction, shallow depth of field, clean warm color grade" That's the gap between unusable content and scroll-stopping UGC. So I built a custom GPT that writes these prompts for you: → Tell it your product (supplement, skincare, SaaS, whatever) → It generates a detailed timeline-based Sora 2 prompt → Shot composition, camera angles, timing breakdowns—all included → Optimized for 9:16 TikTok/Reels format → Copy and paste directly into Sora 2 No guessing. No prompt engineering rabbit holes. No "why does this look terrible" frustration. Professional UGC prompts in 10 seconds. Want free access to the Sora 2 Prompt Generator GPT? > Comment "SORA" > Like this post And I'll send it over (must be following so I can DM)
0:23

This custom GPT writes Sora 2 prompts that actually work 🤯 Most people prompting Sora 2 are getting garbage output. The problem isn't Sora 2. It's your prompts. Here's what I figured out after generating 100+ UGC videos: Sora 2 needs hyper-specific instructions—shot composition, timing, camera movement, lighting, scene details. Most people prompt like this: "Make a UGC video of someone using my skincare product" And then wonder why the output looks like AI slop. What actually gets results: "9:16 vertical handheld shot, soft natural window lighting, female creator mid-20s in bathroom mirror holding [brand] serum at eye level, genuine testimonial energy, 0-3s hook showing application and subtle reaction, shallow depth of field, clean warm color grade" That's the gap between unusable content and scroll-stopping UGC. So I built a custom GPT that writes these prompts for you: → Tell it your product (supplement, skincare, SaaS, whatever) → It generates a detailed timeline-based Sora 2 prompt → Shot composition, camera angles, timing breakdowns—all included → Optimized for 9:16 TikTok/Reels format → Copy and paste directly into Sora 2 No guessing. No prompt engineering rabbit holes. No "why does this look terrible" frustration. Professional UGC prompts in 10 seconds. Want free access to the Sora 2 Prompt Generator GPT? > Comment "SORA" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

13,262 Aufrufe • vor 5 Monaten

GPT 2 images and Seedance 2.0 for animations 🔥😍 creative character sheets and comprehensive Seedance 2.0 multi-shot animation sequences. detailed shot-by-shot with precise timestamps, camera directions, lighting, audio, and constraints Prompts in the Thread 🧵👇👇 try it OpenArt
0:45

GPT 2 images and Seedance 2.0 for animations 🔥😍 creative character sheets and comprehensive Seedance 2.0 multi-shot animation sequences. detailed shot-by-shot with precise timestamps, camera directions, lighting, audio, and constraints Prompts in the Thread 🧵👇👇 try it OpenArt

Dheepan Ratnam

22,771 Aufrufe • vor 23 Tagen

Just tested the new Camera Position feature in FlowbyGoogle You can now shift or adjust your camera view directly inside Flow on any Veo-generated clip. From my experience, it works best on still shots and adds more flexibility to your framing. Currently available for Ultra members only. Curious, how would you make use of this in your videos? 👇
0:32

Just tested the new Camera Position feature in FlowbyGoogle You can now shift or adjust your camera view directly inside Flow on any Veo-generated clip. From my experience, it works best on still shots and adds more flexibility to your framing. Currently available for Ultra members only. Curious, how would you make use of this in your videos? 👇

Dinda Prasetyo

40,430 Aufrufe • vor 7 Monaten

Using Google Labs with Veo 3 to make these. I created a GPT to help you get the right prompt to do this kind of stuff (for free). I'll send you the custom GPT I created if you comment SEND. Must be following so I can send it to you. (takes 15 seconds of work per video)
1:54

Using Google Labs with Veo 3 to make these. I created a GPT to help you get the right prompt to do this kind of stuff (for free). I'll send you the custom GPT I created if you comment SEND. Must be following so I can send it to you. (takes 15 seconds of work per video)

Murray Frost

101,064 Aufrufe • vor 1 Jahr