Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Google AI Studio: Visual Story is very interesting. we are able to create a story with consistent character (s)/setting etc.. I have tried something similar with Dalle3/ChatGPT (multi-frames in 1 image) to keep character & setting consistent... This is next level tho.. brainstorm & create images, then use image-to-video...

anukaakash's profile picture

Anu Aakash

12,701 subscribers

49,503 görüntüleme • 1 yıl önce •via X (Twitter)

EğitimBilim & TeknolojiSanat
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Anu Aakash profil fotoğrafı
Anu Aakash1 yıl önce

*create images individually

Togoda AI Search Engine profil fotoğrafı
Togoda AI Search Engine1 yıl önce

Togoda is Google on Steroids with AI summaries . 🚀 The only thematic AI search engine.👀 It's 100% private with third party proxy. 🧨 Try it today & experience the difference! 👉Follow us @togoda_com 👈 🚀Help us grow & share this post!🚀

madpencil_ profil fotoğrafı
madpencil_1 yıl önce

I was trying with an input ref img to get gemini to create something consistent with it, but it didn't work, asking too much at this point 😆

Uri profil fotoğrafı
Uri1 yıl önce

I should be able to do the full thing with @longstoriesai , I'll post it when it's live!

Resumindo BT profil fotoğrafı
Resumindo BT1 yıl önce

What was the prompt used?

Anu Aakash profil fotoğrafı
Anu Aakash1 yıl önce

[story line] 10 frames, very cinematic, high quality

Heather Cooper profil fotoğrafı
Heather Cooper1 yıl önce

Thank you for sharing this use case! It's very helpful☺️

🍓 Ada profil fotoğrafı
🍓 Ada1 yıl önce

Yo @anukaakash, I’m totally vibing with your excitement about Google AI Studio! 🎨✨ Crafting stories with consistent characters and settings is like giving digital life a narrative heartbeat.

Kol Tregaskes profil fotoğrafı
Kol Tregaskes1 yıl önce

This is amazing.

Stefano Rivera profil fotoğrafı
Stefano Rivera1 yıl önce

Hey, this is a very good idea indeed! Must try it!

Benzer Videolar

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺
1:00

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺

Ideogram

1,712,692 görüntüleme • 10 ay önce

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.
0:25

Creating a consistent scene and character. Seedream is able to edit camera angles from a single reference image. This gives you more control over your video outputs with start and end frames.

Jerrod Lew

26,972 görüntüleme • 9 ay önce

Here's a movie trailer from ChatGPT Images 2.0. Create a storyboard style image with Images 2.0, and use it in Seedream 2.0 as a reference. Enter a prompt to create a 15 second video from the image. The model will use the character and environments. Quick tutorial:
0:27

Here's a movie trailer from ChatGPT Images 2.0. Create a storyboard style image with Images 2.0, and use it in Seedream 2.0 as a reference. Enter a prompt to create a 15 second video from the image. The model will use the character and environments. Quick tutorial:

Jerrod Lew

15,753 görüntüleme • 1 ay önce

Remixing images with AI is so powerful in the design tool I can rebrand any image by going to any logo and prompt: Change to "BRAND NAME”. Also I can create any variation for icons, portraits, mockups, etc.
0:36

Remixing images with AI is so powerful in the design tool I can rebrand any image by going to any logo and prompt: Change to "BRAND NAME”. Also I can create any variation for icons, portraits, mockups, etc.

Meng To

39,767 görüntüleme • 8 ay önce

We are implementing Google's Gemini 1.5 Pro for character description and image generation (with Imagen)! Soon on you'll be able to create character images from text prompts and then bring them to life with Viggle. Stay tuned!
0:35

We are implementing Google's Gemini 1.5 Pro for character description and image generation (with Imagen)! Soon on you'll be able to create character images from text prompts and then bring them to life with Viggle. Stay tuned!

ViggleAI

43,989 görüntüleme • 1 yıl önce

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

67,555 görüntüleme • 11 ay önce

Google Nano Banana is fantastic with character consistency. Combining this with Kling 2.1 start/end frames you can create AI video with much more precision. This tutorial is all done with Freepik, utilizing the new image annotation feature. Hope this helps!
2:09

Google Nano Banana is fantastic with character consistency. Combining this with Kling 2.1 start/end frames you can create AI video with much more precision. This tutorial is all done with Freepik, utilizing the new image annotation feature. Hope this helps!

Jerrod Lew

33,535 görüntüleme • 9 ay önce

Turn a single image into a full story with consistent characters and world design with Story Panels, Panel Upscaler and Gen-4.5 Image to Video.
0:40

Turn a single image into a full story with consistent characters and world design with Story Panels, Panel Upscaler and Gen-4.5 Image to Video.

Runway

19,691 görüntüleme • 4 ay önce

Dollyglot (Dollyglot (YC W25)) is like Character AI but with real-time video avatars. Upload an image and voice to create your AI best friend. Chat with Harry Potter about Hogwarts or brainstorm with The Rock. Congrats on the launch, Thomas Minassian and PHB!
1:26

Dollyglot (Dollyglot (YC W25)) is like Character AI but with real-time video avatars. Upload an image and voice to create your AI best friend. Chat with Harry Potter about Hogwarts or brainstorm with The Rock. Congrats on the launch, Thomas Minassian and PHB!

Y Combinator

72,886 görüntüleme • 1 yıl önce

Seedance 2 is amazing on Mitte!! We tried to offer a more original style with a well-known everyday scene. mitte.ai is An all-in-one visual and video creation suite with AI, geared towards: - professional image and video production - original characters - marketing/social content - stylized visual creation - creative automation... Create your story ! ⬇️ Link below ⬇️
0:26

Seedance 2 is amazing on Mitte!! We tried to offer a more original style with a well-known everyday scene. mitte.ai is An all-in-one visual and video creation suite with AI, geared towards: - professional image and video production - original characters - marketing/social content - stylized visual creation - creative automation... Create your story ! ⬇️ Link below ⬇️

Anima

37,218 görüntüleme • 2 ay önce

AI contents are taking over internet this new Sora Character on Invideo can keep any character super consistent.. place them anywhere, do&talk anything and.. its free and unlimited now 5 examples: 1. create realistic cat asmr video with sound
0:37

AI contents are taking over internet this new Sora Character on Invideo can keep any character super consistent.. place them anywhere, do&talk anything and.. its free and unlimited now 5 examples: 1. create realistic cat asmr video with sound

el.cine

34,455 görüntüleme • 5 ay önce

🚀 Flux from Black Forest Labs is now on RenderNet! Create hyper-realistic, character-consistent images with just one reference image — no LORAs required. Ready to bring your characters to life? Try it with just a few clicks! 🎨✨
1:05

🚀 Flux from Black Forest Labs is now on RenderNet! Create hyper-realistic, character-consistent images with just one reference image — no LORAs required. Ready to bring your characters to life? Try it with just a few clicks! 🎨✨

Affogato AI

59,705 görüntüleme • 1 yıl önce

You can now use rendered frames for image-to-image and image-to-video AI Generation on The Render Network Simply click “Iterate with AI” and instantly create new image + video variations right from the Render job page. No downloads, no switching tabs - just click and create. Try at: Learn more:
0:43

You can now use rendered frames for image-to-image and image-to-video AI Generation on The Render Network Simply click “Iterate with AI” and instantly create new image + video variations right from the Render job page. No downloads, no switching tabs - just click and create. Try at: Learn more:

The Render Network

37,093 görüntüleme • 1 yıl önce

Want to create a consistent AI influencer vlog that actually looks professional? Skip the endless retakes, awkward movements, and changing character looks. Use a simple proven workflow: ➡️ AI Influencer → First Frame → Guide Image → Prompt → Video The result is smoother transitions, stronger character consistency, and vlog content that feels natural from start to finish. Try it FREE
0:30

Want to create a consistent AI influencer vlog that actually looks professional? Skip the endless retakes, awkward movements, and changing character looks. Use a simple proven workflow: ➡️ AI Influencer → First Frame → Guide Image → Prompt → Video The result is smoother transitions, stronger character consistency, and vlog content that feels natural from start to finish. Try it FREE

AyeshaAi

37,862 görüntüleme • 13 gün önce

this is how we do ads in 2026 you just need 3 images to generate a studio level product ad in hrs and.. keep character, outfit, product and bg consistent
0:23

this is how we do ads in 2026 you just need 3 images to generate a studio level product ad in hrs and.. keep character, outfit, product and bg consistent

el.cine

466,676 görüntüleme • 4 ay önce

Check out CAT3D! Image(s)-to-3D in 1 minute! Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.
0:38

Check out CAT3D! Image(s)-to-3D in 1 minute! Given any number of real or generated images, CAT3D uses a multi-view diffusion prior to create consistent novel views. These views are used to reconstruct a 3D scene using NeRF/3DGS.

Philipp Henzler

12,737 görüntüleme • 2 yıl önce

Create amazing action scenes with Seedance 2.0! First, create your character sheet with ChatGPT Images 2.0, then bring it to Seedance 2.0 as a reference image. Prompt your scene and what happens, referencing the character. More details + prompts below.
0:28

Create amazing action scenes with Seedance 2.0! First, create your character sheet with ChatGPT Images 2.0, then bring it to Seedance 2.0 as a reference image. Prompt your scene and what happens, referencing the character. More details + prompts below.

Jerrod Lew

15,877 görüntüleme • 1 ay önce