Vivago Video Agent - Skip the prompting. Produce consistently compelling videos.
by•
Vivago Video Agent lets you generate consistently compelling narrative videos with natural language. No more annoying prompting!
Our video agent ensures every scene stays on-brand and internally coherent by guiding you through a structured creative process. Just share your assets and describe your story — a swarm of AI directors will invent characters and write a compelling story for you.
See the keyframes before rendering. Your 1-min 1080P story video will be ready in 40 mins.
Replies
Vivago
Hi Product Hunt community! 👋
I’m Zijian, a Senior Product Manager at Vivago. It’s a huge honor to be back here!
@Vivago reached the Top 3 Product of the Day 2 years ago thanks to your incredible support. We've pushed even further, and today, I’m thrilled to announce the Vivago Video Agent.
Vivago Video Agent lets you generate consistently compelling narrative videos with natural language. No more annoying prompting!
We used only 2 ingredients to tell the very compelling story: one PH Kitty image + one sentence.
Our video agent ensures every scene stays on-brand and internally coherent by guiding you through a structured creative process.
1. Share your assets and describe your story.
2. A swarm of AI directors invents characters and writes a compelling story for you.
3. See the keyframes before the video is rendered.
4. Your 1-min 1080P story video will be ready in 40 minutes.
To celebrate our return to the community, we have a special gift for the first 500 PH members!
Use code “1MPRO4PH” at checkout to claim 1 Month of Plus Membership for FREE (valid thru May 31). We’d love to hear your feedback on our new "AI Director" workflow.
I’ll be here all day to answer your questions!
Keep creating,
Zijian
@zijian Congrats on the launch and #1 Product of the Day!
The AI Director workflow sounds interesting, especially the part where users can review keyframes before rendering. That seems like a practical way to reduce the usual trial-and-error in AI video generation.
One question: how much control does the user have over changing the story direction or visual style after the keyframes are generated?
Raycast
@bsy0221 kicked off our first call by demoing the Vivago Video Agent on me — fed it my profile pic and a one-line prompt (something like "superhero story, heavy dialogue, multiple twists, ~1 minute, live action").
Out came a narrative video where I'm the hero squaring off against a villain named Evelyn:
It also decided my name was Arthur. My Future Camelot alter ego, apparently.
Consider this was produced with a single still and low effort prompt, I was impressed given all my failed attempts to get @Sora by OpenAI (RIP) to do my bidding!
Think Claude Code, but for video.
A swarm of AI directors (picture assistant, creative assistant, director, art assistant, etc) handle the conversational back-and-forth so you skip the prompt-wrestling and just describe the story you want to tell.
Their proprietary Hi-Dream-01 model is ranked #1 on the ArtificialAnalysis leaderboard, and the agent can reach for @Seedance AI Video Generator, @Google Nano Banana Pro, or @Gemini when those fit the goal.
If you've been burned by stitching together 4-second clips that don't cohere, Vivago is built for narrative — 15s to 60s today, with 3 minutes on the roadmap.
Agnes AI
@bsy0221 @chrismessina Now Marvel cosmo should invite Dr Arthur to their squad !
Vivago
@lakshminath_dondeti
Great question!
Traditionally, you have to describe every frame, camera angle, and style parameter yourself. With Vivago, you skip all of that.
You just type a simple story idea in natural language. Then, our built-in 'swarm of AI directors' takes over. They automatically brainstorm the characters, break down the scenes, and write a cohesive creative logic for you.
Before the heavy rendering begins, the tool presents a 9-frame storyboard preview so you can see exactly what the creative direction looks like. It gives you 100% confidence in the output without doing the heavy lifting of prompt engineering!
Vivago
@lakshminath_dondeti
Hhhh, love that analogy! You hit the nail on the head.
Just like Claude Code is transforming prompt-heavy coding into autonomous, agent-driven execution, we believe video production deserves the exact same evolution.
Human creators spending hours wrestling with prompt engineering doesn't make sense at all. We are not born to code, but born to create. We'd like to give them an intelligent, coordinated swarm that understands creative intent and handles the production heavy-lifting.
Thanks for the brilliant take!
HeyForm
Congrats on the launch!
I've been tracking the AA leaderboard and noticed HiDream-O1-Image at No. 1 for a while. Seeing it used as the backbone here explains why the visual coherence is so strong, the characters actually look like themselves from frame 1 to 50. Impressive engineering!
Vivago
@itsluo
Wow, thanks for the shoutout!
Coming from you, this means a ton to our engineering team.
We're super proud of how HiDream-O1-Image performs as the backbone. Beyond the model itself, we actually built an entire 'swarm of AI directors' workflow around it this time. It acts like a real creative studio to plan the scenes and map the visuals before rendering, which is how we pushed the boundary to a stable 3-minute output.
Appreciate you stopping by!
Solid work! The 9-frame storyboard preview before render looks like the smartest bit. After I approve those keyframes, is the 1-min render locked to them?
Vivago
@artstavenka1
Love that you noticed the storyboard logic!
Let me share a quick insider update on how our architecture scales up from short to long-form storytelling:
For our 15-second mode, yes, it relies heavily on that 9-frame storyboard blueprint to lock coherence. But for our full 1-minute narrative mode, we actually upgraded to a much more advanced, film-industry-style pipeline!
Instead of boxing the AI into a rigid 9-frame grid for long stories, our unified planning layer takes your story script and pre-generates a cohesive set of 'Global Production Assets' - including character sheets, environmental concepts, and key props, etc.
Our core agent framework then uses these unified reference assets as absolute anchor points to guide the continuous rendering of the full 1-minute video straight from the script. This gives our workflow much more creative freedom for dynamic camera tracking while ensuring zero character drift. It’s total control, just scaled up for true cinematic production! 🎬
Congrats on the launch team
does the AI director workflow let you iterate? Like if you get keyframes back and want to explore a different angle on the same story, can you guide it without starting from scratch?
Vivago
@boyuan_deng1
You nailed the exact core of our product vision!
Yes, iteration is absolutely at the heart of our AI Director workflow.
For our standard 15-second creation mode, we fully support up to 10 rounds of back-and-forth dialogue to freely tweak and modify the generated content.
And it gets even better. For our longer 3-minute storytelling mode (currently in Beta), we’ve unlocked a completely unrestricted, natural language dialogue system. This allows you to interactively guide, iterate, and refine any specific stage or frame of the production process just by talking to it.
No starting from scratch required!
Triforce Todos
The coherence across frames looks solid. How much of that comes from hiDream-O1 itself vs. your planning layer?
Vivago
@abod_rehman
Appreciate the sharp question!
Vivago is built from the ground up as an agent-native product.
We’ve architected a proprietary three-tier agent system consisting of 'Tools + Skills + Workflows,' all orchestrated by a single, unified planning layer that schedules all core capabilities dynamically.
The magic is that our agent framework is natively integrated right into the core architecture of the HiDream-O1 model itself.
So rather than a chaotic struggle between model power and prompt layers, it’s a seamless synergy where the model naturally understands and executes the structured agent logic.
Earth.fm
Really impressed by how smooth the video generation looks 👀
The 4K enhancement feature sounds super useful for creators. How long does an average video take to generate?
Vivago
@1mirul
Thanks for the love! Glad you like the smoothness. 🙌
Just a quick clarification to keep expectations aligned: Vivago currently renders native 1080P video rather than 4K.
Regarding the rendering speed:
a standard 15-second video takes about 10 minutes, while a more complex 1-minute narrative takes around 40 to 50 minutes.
Because our 'AI Directors' are doing heavy, frame-by-frame orchestration and visual continuity alignment behind the scenes, it takes a bit of time to bake.
But we promise the coherent quality is absolutely worth the wait! 🎬
CheckYa
so wait... i just give it a photo and a sentence and it makes a whole video? that seems too good to be true lol. what's the catch here? does it actually look good or is it one of those things where the demo videos are cherry-picked?
Vivago
@monir_
Haha, I totally respect the skepticism! The AI space is flooded with hyper-curated clips, so it's 100% fair to ask 'what's the catch?'
To be honest, we are so confident in our backbone that I'm not even going to waste your time trying to convince you with another official demo. Instead, I challenge you to go break it yourself. 😉
Get 1-month free membership with code "1MPRO4PH", upload a photo of yourself, and describe your story.
You can retry the same description & images we used for this demo video as well:
Description: A kitten travels through a highly futuristic digital frontier, searching for Arthur and inviting him to become the legendary Product Hunter for the global launch of the vivago Agent website.
Chris (our No. 1 hunter) profile photo can be found here: https://messina.as.me/schedule/9ce1ce24/appointment/60975938/calendar/9937930
Product Hunt Kitty image we used is this one:
https://elev.io/blog/featured-on-product-hunt-what-we-did-right-and-what-wed-change
The only real 'catch' right now is that a full 1-minute narrative takes about 40-50 mins because the agent swarm is doing heavy frame-by-frame coherence plotting. But the output is raw and real.
Let us know if we passed your BS test!🚀
Can i use my own character designs, or does the swarm create everything from scratch? Love this approach, congrats on the big launch
Vivago
@imogen_wallace
Thank you so much for the congrats! You just hit on one of my favorite features. ❤️
YES, you absolutely can use your own character designs! In fact, I just used photos of myself and my cats to generate my own story earlier today.
While our 'swarm' is brilliant at brainstorming characters from text, we designed Vivago specifically for real creators who already have fixed IPs. For our long-form mode, you can upload your own character images, reference sheets, or environmental designs right into the pipeline.
Our planning layer locks those visual identities first, and then the agent swarm directs the rest of the storytelling around YOUR assets. This ensures your character stays consistent across every single frame. Go grab the 1-month free Pro code on our page and bring your own characters to life! 🎬⚡
It won't take you too long, so you are more than welcome to post your video onto YouTube & share the link here with the community!