Wireflow AI

Your team and AI agents making ADs together

[Wireflow AI @wireflowai]

Google's Gemini Omni 1.2 Flash is now live on Wireflow.

Every shot in this video was made with it:
→ 15 second scenes with lip-synced dialogue
→ edit any shot with one sentence
→ up to 6 reference images to keep characters consistent
→ first and last frame control
→ up to 4K, or draft at 360p for about 2¢ a second

Try it: https://t.co/bB6W5NHg1Z

What would you make with it?

[Google @Google]

Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬

Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale:

⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K

⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s

💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch

🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync

🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts

See these updates in action ↓

[Wireflow AI @wireflowai]

Kling 4.0 Flash is now live on Wireflow.

→ Set Model to Flash on the Kling 4.0 card

→ 5 second 720p clip: 54 credits, vs 91 on Kling 4.0

→ 3 to 20 seconds from a prompt, a start frame or up to 10 reference images

→ Edits clips up to 20 seconds

https://t.co/ccKH07n8Mb

What would you draft first at 41% fewer credits?

[Wireflow AI @wireflowai]

@dex_elite @Sonofpeace0001 One small bug which has been fixed

[Wireflow AI @wireflowai]

@davidim

[Wireflow AI @wireflowai]

@LinusEkenstam We did a thing too. Making this into an api

[Wireflow AI @wireflowai]

No video models were used in this scene.

Our agent built the whole room in Blender code: the rain on the window, the warm lamp, the light bouncing off the walls, the slow push-in.

On a cloud GPU that's about 4 cents a clip. Five seconds from a video model runs about $1.80.

We're putting this behind an API: describe a scene, get the shot back.

What would you build first?

[Wireflow AI @wireflowai]

@AndyAI_ @hyperspell So good happy to help cook this up it’s getting to easy to make these :yawn:

Cmon @michaelaubry and Andy give me harder videos to make I’m begging

[Wireflow AI @wireflowai]

@rileybrown Been there done that

[Wireflow AI @wireflowai]

@myles_franklin @rileybrown Doesn’t load are you talking about ig lol

[Wireflow AI @wireflowai]

@NFTsQueen2 @Sonofpeace0001 At a certain point we cannot take a loss though we wouldn’t be in business

I do plan on offering drivers for those who have 4090s and above to run some open models within our system

[Wireflow AI @wireflowai]

@ninjaa_xyz @Sonofpeace0001 We use anthropic for the on site llm

We’re a visual builder and support gpt 2.6

[Wireflow AI @wireflowai]

@AndyAI_ Experimental atm but I think we may wire some stuff up and make 3d animation more accessible

More control and ideally cheaper costs

[Wireflow AI @wireflowai]

No video models were used in this scene.

Our agent built the whole room in Blender code: the rain on the window, the warm lamp, the light bouncing off the walls, the slow push-in.

On a cloud GPU that's about 4 cents a clip. Five seconds from a video model runs about $1.80.

We're putting this behind an API: describe a scene, get the shot back.

What would you build first?

[Wireflow AI @wireflowai]

@AndyAI_ @andrewxroas Connect the MCP now and we’ll give you some credits to cook

https://t.co/CsIe8JEzS5

[Wireflow AI @wireflowai]

@NFTsQueen2 @Sonofpeace0001 Yes GPUs are expensive. We’re working on making video editing cheaper and compositor

Many models cost a lot

What are you using it for I’ll look into it

[Wireflow AI @wireflowai]

Try Gemini Omni 1.2 Flash on Wireflow:

Text to video: https://t.co/mWd1iwjny3

Image to video (first + last frame): https://t.co/Iy1Hcuzyn6

Reference images to video: https://t.co/ETFyR4d0LU

Video edit: https://t.co/z2mnJALi9W

[Wireflow AI @wireflowai]

Google's Gemini Omni 1.2 Flash is now live on Wireflow.

Every shot in this video was made with it:
→ 15 second scenes with lip-synced dialogue
→ edit any shot with one sentence
→ up to 6 reference images to keep characters consistent
→ first and last frame control
→ up to 4K, or draft at 360p for about 2¢ a second

Try it: https://t.co/bB6W5NHg1Z

What would you make with it?

[Google @Google]

Meet Gemini Omni 1.2 Flash, our updated video generation model from @GoogleDeepMind 🎬

Get stronger consistency, more creative control, and faster, more cost-effective video creation at scale:

⚡ Fast & 30% lower cost: Draft at 360p or 720p ($0.07/s) and upscale to 1080p or 4K

⏱️ Longer clips: Generate and edit videos up to 15s, or pick any exact length from 3s to 15s

💬 Edit in conversation: Swap backgrounds, subjects, or lighting turn by turn without starting over from scratch

🗣️ More natural speech: Create fluid, multi-speaker dialogue with clearer lip-sync

🎬 More controllable shots: Direct continuous camera moves with fewer jump cuts

See these updates in action ↓

[Wireflow AI @wireflowai]

Try it here:
Sunburst Text-to-Image

https://t.co/3KHRldxYAx

Sunburst Edit

https://t.co/8z4xzh1alE

Flare Text-to-Image

https://t.co/KrqH4zjd6Z

Flare Edit
https://t.co/Q7VxY6GNBD

[Wireflow AI @wireflowai]

GPT Image 2.6 lets you draw on any photo and it makes it real.

Everyone's demoing lamps and cats. We gave this guy a Lamborghini, a gold chain and two friends.

Live on Wireflow. What would you draw on him?

[OpenAI @OpenAI]

Images, upgraded—introducing ChatGPT Images 2.6.

Now with GIFs and reference images.

Plus, two new models are coming to the API with 50% faster image generation.

[Wireflow AI @wireflowai]

@michaelaubry Proud to make this possible. Amazing you account on instagram is blowing up

Keep it up and you’ll be in the hundreds of thousands of followers in no time

[Wireflow AI @wireflowai]

Who’s next?

[Michael Aubry @michaelaubry]

YC startups ship every day and launch in silence.

So I'm making one launch video a day for a startup that deserves it.

Day 1: @AsideAI, the browser built to do real work for you. cc @hyojun_at

Reply with yours and you might be next.

[Wireflow AI @wireflowai]

Try Kling 4.0 on Wireflow today. Text, image and reference to video in one node:
https://t.co/hLnxCYVCZT

[Wireflow AI @wireflowai]

Kling 4.0 is now live on Wireflow.

The latest model from @Kling_ai brings:

• Up to 30 seconds of video with sound

• Up to 10 reference images to keep characters and props consistent

• Start and end frame control

• 720p or 1080p