正在加载视频...

视频加载失败

返回首页

Here's my meta-prompt to generate consistent scenes for Veo 3. It ensures everything from character styling to set pieces are consistent across multiple scenes/generations. Use it w/ a LLM, and pass the LLM's output to Veo!

mattshumer_'s profile picture

Matt Shumer

366,894 subscribers

41,089 次观看 • 1 年前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Matt Shumer 的头像
Matt Shumer1 年前

Prompt here:

Matt Figdore 的头像
Matt Figdore2 年前

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Jason Kuperberg 的头像
Jason Kuperberg1 年前

matthew.. what are those things running across the top haha???

Matt Shumer 的头像
Matt Shumer1 年前

i told you... needed a lil surprise and delight

BEN SYNE 的头像
BEN SYNE1 年前

This is great📈

Ion Brinzila 的头像
Ion Brinzila1 年前

Matt, you have nothing about shots vs scenes, and I meant it’s better to instruct to divide a scene into shots for up to 8 seconds each, it’s a much more appropriate term given the tech limits

Jose 的头像
Jose1 年前

Another powerful approach for even more control (and amazing results) is combining: ChatGPT for images + Kling AI (Elements) for video + ElevenLabs V3 for voices.

Altiam Kabir 的头像
Altiam Kabir1 年前

Great method for maintaining consistency! Can't wait to see the creative results.

jason 的头像
jason1 年前

veo 3 is insane but i still can't get consistent faces without heavy post-processing. lmk if this works better for you.

相关视频

VEO-3's Image to Video with Audio is a massive gamechanger for AI Storytelling. Full Scenes with consistent characters are here. PLUS MORE in the thread!
0:24

VEO-3's Image to Video with Audio is a massive gamechanger for AI Storytelling. Full Scenes with consistent characters are here. PLUS MORE in the thread!

Theoretically Media

67,582 次观看 • 1 年前

One prompt. Multiple gaming scenes 🎮 The Nano Banana agent can generate several images at once, using a reference image to keep the same person consistent across scenes. This example spans different gaming eras, but the same approach works for any theme or style. Images and videos, all in one place. Agent + prompt 👇
0:24

One prompt. Multiple gaming scenes 🎮 The Nano Banana agent can generate several images at once, using a reference image to keep the same person consistent across scenes. This example spans different gaming eras, but the same approach works for any theme or style. Images and videos, all in one place. Agent + prompt 👇

GLIF

10,882 次观看 • 6 个月前

I made a perfume ad in minutes with Nano Banana + VEO 3 With Nano Banana and VEO 3 you can create ads in just minutes Characters stay consistent across scenes Locations remain coherent and realistic Products created from scratch and integrated into the ad Here’s how I did it🧵👇
0:31

I made a perfume ad in minutes with Nano Banana + VEO 3 With Nano Banana and VEO 3 you can create ads in just minutes Characters stay consistent across scenes Locations remain coherent and realistic Products created from scratch and integrated into the ad Here’s how I did it🧵👇

MayorkingAI

99,579 次观看 • 10 个月前

How To Use Google Flow to Create Consistent AI Characters & Videos | Full Tutorial for Beginners. In this video, you'll learn how to create consistent AI characters, generate images and videos with Nano Banana and Gemini Omni Flash, use Frames and Ingredients, and build longer AI video scenes while keeping character consistency across different shots. This information is for both new and existing Youtube creators, who want to learn how to create consistent characters for your story scenes. Like, Retweet and Bookmark. Follow BIG CHRIS
9:25

How To Use Google Flow to Create Consistent AI Characters & Videos | Full Tutorial for Beginners. In this video, you'll learn how to create consistent AI characters, generate images and videos with Nano Banana and Gemini Omni Flash, use Frames and Ingredients, and build longer AI video scenes while keeping character consistency across different shots. This information is for both new and existing Youtube creators, who want to learn how to create consistent characters for your story scenes. Like, Retweet and Bookmark. Follow BIG CHRIS

BIG CHRIS

12,474 次观看 • 1 个月前

You can just ask Perplexity Comet to generate a video for you using Veo 3 inside Gemini 🙂 You can either give a detailed prompt with steps or just keep it simple like this, both work: Comet Prompt: You have access to the Gemini interface, use it to generate a video and wait for rendering to complete. Prompt: It figures out the rest. Where to paste the prompt, whether to click the video option, everything. Pretty smart.
0:21

You can just ask Perplexity Comet to generate a video for you using Veo 3 inside Gemini 🙂 You can either give a detailed prompt with steps or just keep it simple like this, both work: Comet Prompt: You have access to the Gemini interface, use it to generate a video and wait for rendering to complete. Prompt: It figures out the rest. Where to paste the prompt, whether to click the video option, everything. Pretty smart.

AshutoshShrivastava

35,501 次观看 • 1 年前

Step into the director's chair! 🎥 Direct avatars with precision using Veo 3.1, placing them into specific scenes to interact with uploaded images of your products while maintaining a consistent face and voice across every frame. Try it at
0:31

Step into the director's chair! 🎥 Direct avatars with precision using Veo 3.1, placing them into specific scenes to interact with uploaded images of your products while maintaining a consistent face and voice across every frame. Try it at

Google Workspace

51,406 次观看 • 3 个月前

Google Veo 3 understands spatial prompts. Upload an image with some annotations and ask Veo 3 to follow the instructions in your prompt. Here's how to do it, and some examples.
0:45

Google Veo 3 understands spatial prompts. Upload an image with some annotations and ask Veo 3 to follow the instructions in your prompt. Here's how to do it, and some examples.

Jerrod Lew

110,675 次观看 • 1 年前

🚨 How to make longer videos with Veo 3: I've spent hours experimenting with the new image-to-video mode. And I've found a way to generate consistent + cohesive stories that are much longer than the 8 second limit. Tutorial and tips to make it work 👇
0:38

🚨 How to make longer videos with Veo 3: I've spent hours experimenting with the new image-to-video mode. And I've found a way to generate consistent + cohesive stories that are much longer than the 8 second limit. Tutorial and tips to make it work 👇

Justine Moore

317,413 次观看 • 1 年前

We’re bringing identity consistency to Veo 3.1. For the first time ever, you have complete control of your Veo generations across every voice, character, and scene. With HeyGen’s avatar technology, generate once in Veo 3.1 and your avatar stays consistent, keeping your real voice and true look every time. Voice Consistency: Choose your voice, and HeyGen blends your real tone into Veo’s cinematic motion. Multi-Scene Consistency: Seamless transitions between scenes, one identity, endless stories. Character Consistency: Keep using that avatar with consistent voice and appearance to create unlimited videos in different outfits, styles and environments This is what happens when the world’s best video generator meets the best avatar technology. Don’t just make a scene. Free your story.
1:52

We’re bringing identity consistency to Veo 3.1. For the first time ever, you have complete control of your Veo generations across every voice, character, and scene. With HeyGen’s avatar technology, generate once in Veo 3.1 and your avatar stays consistent, keeping your real voice and true look every time. Voice Consistency: Choose your voice, and HeyGen blends your real tone into Veo’s cinematic motion. Multi-Scene Consistency: Seamless transitions between scenes, one identity, endless stories. Character Consistency: Keep using that avatar with consistent voice and appearance to create unlimited videos in different outfits, styles and environments This is what happens when the world’s best video generator meets the best avatar technology. Don’t just make a scene. Free your story.

HeyGen

1,864,232 次观看 • 10 个月前

To use it simply go to Google Flow, sign up for the "Ultra" account and set the quality to "Highest Quality - Veo 3"
0:51

To use it simply go to Google Flow, sign up for the "Ultra" account and set the quality to "Highest Quality - Veo 3"

Mark Gadala-Maria

177,393 次观看 • 1 年前

Nano Banana + Veo 3 + n8n is absolutely WILD 🤯 This AI system creates UGC videos with consistent characters & product shots at scale. And auto-stitches everything together into finished content. Perfect for e-comm operators & creative agencies who need brand consistency. Just upload ONE product image and get complete UGC campaigns with the same character across all videos. Here's how it works: → Upload product image via n8n form → AI analyzes your product automatically → Nano Banana generates consistent character variations → Veo 3 creates multiple video scenes with same talent → Auto-combines all clips into final campaign video → Ready-to-download UGC content in minutes Built 100% in n8n. Fully automated character consistency. Want the complete n8n workflow? Comment "BANANA" + like and I'll send it over (must be following so I can DM)
0:26

Nano Banana + Veo 3 + n8n is absolutely WILD 🤯 This AI system creates UGC videos with consistent characters & product shots at scale. And auto-stitches everything together into finished content. Perfect for e-comm operators & creative agencies who need brand consistency. Just upload ONE product image and get complete UGC campaigns with the same character across all videos. Here's how it works: → Upload product image via n8n form → AI analyzes your product automatically → Nano Banana generates consistent character variations → Veo 3 creates multiple video scenes with same talent → Auto-combines all clips into final campaign video → Ready-to-download UGC content in minutes Built 100% in n8n. Fully automated character consistency. Want the complete n8n workflow? Comment "BANANA" + like and I'll send it over (must be following so I can DM)

Mike Futia

283,219 次观看 • 10 个月前

ai ugc yapping is fire. this is one of the craziest videos i've done. - generate character - generate video - generate multiple consistent videos that's it. here's a recent video i did with my V3 System:
0:24

ai ugc yapping is fire. this is one of the craziest videos i've done. - generate character - generate video - generate multiple consistent videos that's it. here's a recent video i did with my V3 System:

0x ROAS

66,757 次观看 • 2 个月前

Same character. Infinite possibilities. ✨ NovelAI's Character Reference brings your OCs to life across endless scenes and poses—perfectly consistent, every time. Start For Free Now👇
0:29

Same character. Infinite possibilities. ✨ NovelAI's Character Reference brings your OCs to life across endless scenes and poses—perfectly consistent, every time. Start For Free Now👇

NovelAI

26,906 次观看 • 8 个月前

I got early access to Runway's new Gen-4 References and it's incredible! Upload a single reference image to maintain consistent characters across scenes in multiple poses. You can prompt to continue in the same setting, focus on a specific area of the background, or match the color and tone. Here are some of my first results using the same character in different settings:
0:33

I got early access to Runway's new Gen-4 References and it's incredible! Upload a single reference image to maintain consistent characters across scenes in multiple poses. You can prompt to continue in the same setting, focus on a specific area of the background, or match the color and tone. Here are some of my first results using the same character in different settings:

Heather Cooper

17,223 次观看 • 1 年前

New to Featured Workflows: Seamless Transitions. Now you can create multiple generations with a single consistent subject interacting with different objects across various scenes and environments. All in a single, easy to use Workflow without the need for complex prompting. Explore the full collection of Featured Workflows or create your own at
0:35

New to Featured Workflows: Seamless Transitions. Now you can create multiple generations with a single consistent subject interacting with different objects across various scenes and environments. All in a single, easy to use Workflow without the need for complex prompting. Explore the full collection of Featured Workflows or create your own at

Runway

52,203 次观看 • 7 个月前

Prompting with Sora's storyboard mode is an incredible way to generate scenes. Here's a 20 second clip with multiple shots generated from just one prompt!
0:22

Prompting with Sora's storyboard mode is an incredible way to generate scenes. Here's a 20 second clip with multiple shots generated from just one prompt!

Ammaar Reshi

17,035 次观看 • 1 年前

All the secrets of nano banana and Veo 3 Fast to achieve: · consistent characters and scenes · cinematic angles · integration of extra elements in this LTX Studio thread 🧵👇 Wanna help me finish the story?
1:00

All the secrets of nano banana and Veo 3 Fast to achieve: · consistent characters and scenes · cinematic angles · integration of extra elements in this LTX Studio thread 🧵👇 Wanna help me finish the story?

TechHalla

34,110 次观看 • 10 个月前

consistent characters + mood in Google Veo 3... it’s possible ✨ I used to spent hours refining text-to-image prompting (mostly in midjourney) trying to keep character and tone consistent – now I’m trying the same in T2V, seeing how far I can push visual continuity using just words here's what's been working for me so far 🧵
0:20

consistent characters + mood in Google Veo 3... it’s possible ✨ I used to spent hours refining text-to-image prompting (mostly in midjourney) trying to keep character and tone consistent – now I’m trying the same in T2V, seeing how far I can push visual continuity using just words here's what's been working for me so far 🧵

Julie W. Design

123,668 次观看 • 1 年前

Runway Aleph experiment: using one initial vid clip as a character 'video reference' to generate many more with consistent aesthetics/world Whole video is made from aleph generations based on one initial clip (prompt and clip in the comments)
0:53

Runway Aleph experiment: using one initial vid clip as a character 'video reference' to generate many more with consistent aesthetics/world Whole video is made from aleph generations based on one initial clip (prompt and clip in the comments)

Ray (movie arc)

30,361 次观看 • 1 年前

Google Veo 3.1 has an update! Using the Gemini App you can use multiple image references to create your final video. Combine this with a text prompt to keep consistency over characters or products. Here's how to do it.
0:20

Google Veo 3.1 has an update! Using the Gemini App you can use multiple image references to create your final video. Combine this with a text prompt to keep consistency over characters or products. Here's how to do it.

Jerrod Lew

39,491 次观看 • 6 个月前