Kinetix

3D & Human Motion Intelligence Research Lab

Learn more:

[Kinetix @kinetix_ai]

Kamo-1 is officially live in Open Beta and it pushes AI video into a new vertical: control.

Most models chase fidelity. Kamo-1 focuses on performance control & direction.

• Act out a motion → get the full-body performance
• Choose camera trajectory → get real cinematography

Check it out: https://t.co/ThELubzcdb

Comment “Character motion & camera control” in the first 24 hours to get 300 credits!

[Kinetix @kinetix_ai]

@Artedeingenio Super nice moves! Thanks for the mention

[Everett World @WorldEverett]

Imagine this: you have a great idea for an AI video.

You’re excited to bring it to life… and then you lose hours rerolling generations just to get close to what you had in mind.

Sound familiar? It’s happened to me more times than I can count - and it’s a real creative bottleneck.

That’s why Kamo-1 by @kinetix_ai genuinely surprised me. Instead of endless rerolls, it lets you generate precise videos based on an input clip. You create the first frame, choose the camera controls, and the results actually follow your intent.

Long-term, this kind of control and predictability will get much closer to how traditional CGI workflows work.

Check out my guide below on how I’m using it 👇

[Kinetix @kinetix_ai]

Super cool @Uncanny_Harry

Street Fighter hits different

[Uncanny Harry AI @Uncanny_Harry]

I spent far too much time playing Street Fighter with my mates in my early 20's. So when I partnered with @Kinetix_ai to explore their updated Kamo-1 model, which is now in early Beta, I decided to give a few Street Fighter characters a test drive. In the bottom left you can see the video I recorded of myself which drives the actions of the character and in bottom left the image i generated with Seedream. The main video are the driving video combined with the image, a text prompt and a camera template. This brings real control to your generations, you make the prompt image, you control the character and the camera. The model is in open Beta now, so you can check it out for yourself.

[Kinetix @kinetix_ai]

@ZePatriote_2 For the moment, you can only control 1 character with an acting video. If other characters are visible in the first frame, you can still prompt their movements.

Transparent / alpha exports are on the roadmap!

[Kinetix @kinetix_ai]

Daily Kamo-1 Clip

Today’s clip demonstrates how Kamo-1 uses a simple acting input, one reference frame, and a selected camera movement to produce a controlled, coherent shot.

Controllable generation follows a simple structure:
• your image builds the scene
• your acting video drives the motion
• your camera preset sets the shot

We’ll be sharing more this week. Let us know what we should test next!

[Kinetix @kinetix_ai]

@Artedeingenio Can't wait to see your experiments!

[Kinetix @kinetix_ai]

Kamo-1 = your motion + your camera + your scene. The first AI video model designed for control, not noise.

[Kinetix @kinetix_ai]

@umesh_ai @LeonardoAi Wild level of micro-detail here 🔬

[Umesh @umesh_ai]

The one thing missing from your (reference image + acting video) is camera movement.

Kinetix brings this to life.

[Kinetix @kinetix_ai]

@umesh_ai 🫶

[Kinetix @kinetix_ai]

Daily Kamo-1 Clip

Today’s example shows how Kamo-1 takes a basic acting video, one reference image, and a chosen camera preset, and combines them into a fully controlled generation.

This is the core of controllable generation:
• the scene → shaped by your image
• the motion → guided by your performance
• the camera → chosen from 30+ presets

More clips on the way this week. Tell us what you’d like to see next!

[Kinetix @kinetix_ai]

@umesh_ai Thanks for the support! 🫶

[Kinetix @kinetix_ai]

@julianjenkins We do! As long as the character has a human-like form - try it out :)

[Kinetix @kinetix_ai]

Daily Kamo-1 Clip

Today’s clip shows how Kamo-1 takes a simple acting video, a single reference frame, and a chosen camera preset, and turns them into a fully controlled generation.

What you’re seeing here is the essence of controllable generation:
• the scene → built from your image
• the motion → driven by your performance
• the camera → selected from 30+ options

More clips coming this week. Tell us what you want to see next!

[Kinetix @kinetix_ai]

Daily Kamo-1 Clip 🎥

Today’s clip shows how Kamo-1 takes a simple acting video, a single reference frame, and a chosen camera preset, and turns them into a fully controlled generation.

What you’re seeing here is the essence of controllable generation:

• the scene → built from your image
• the motion → driven by your performance
• the camera → selected from 30+ options

More clips coming this week. Tell us what you want to see next!

[Kinetix @kinetix_ai]

Awesome creations by @WorldEverett with our model Kamo-1. Check it out! 👇

[Everett World @WorldEverett]

One of the hardest things to achieve with AI is precise character motion.

The new model by @kinetix_ai, Kamo-1, is amazing at giving you far more control over your generations.

It’s also the first 3D-conditioned model, so it understands the scene in 3D and gives you almost unlimited camera motion.

Let me show you how to use it 👇

[Everett World @WorldEverett]

One of the hardest things to achieve with AI is precise character motion.

The new model by @kinetix_ai, Kamo-1, is amazing at giving you far more control over your generations.

It’s also the first 3D-conditioned model, so it understands the scene in 3D and gives you almost unlimited camera motion.

Let me show you how to use it 👇

[Kinetix @kinetix_ai]

Daily Kamo-1 Clip 🎥

Today’s clip shows how Kamo-1 takes a simple acting video, a single reference frame, and a chosen camera preset, and turns them into a fully controlled generation.

What you’re seeing here is the essence of controllable generation:
• the scene → built from your image
• the motion → driven by your performance
• the camera → selected from 30+ options

More clips coming this week. Tell us what you want to see next!

[Kinetix @kinetix_ai]

@Lex_Murat We're focusing on providing higher camera control! More to come soon... 📹

[Kinetix @kinetix_ai]

Daily Kamo-1 Clip 🎥

Today’s clip shows how Kamo-1 takes a simple acting video, a single reference frame, and a chosen camera preset, and turns them into a fully controlled generation.

What you’re seeing here is the essence of controllable generation:
• the scene → built from your image
• the motion → driven by your performance
• the camera → selected from 30+ options

More clips coming this week.

Tell us what you want to see next!