Reid Hannaford demonstrates a workflow using Blender 3D blocking to control camera trajectories in Seedance 2.0 AI video

“This is the difference between describing a shot and directing one.”

Video models are getting so good that people are finally getting 3d pilled

Way more fun to grab a phone and record the exact camera move you want vs. endlessly hitting the slot machine

@thealphatron Thank you! Seedance is actually pretty good at just intuiting the space based on the start frame, but I also mention the colors of the boxes in my prompt.

I posted my full prompt here:

@kenyondigital Yeah! Nothing too crazy, just basic shapes in blender. Everything is just cubes. I used fSpy to match the camera's focal length from the start frame and then just roughly dropped in the cubes to match the shot.

And here's my full prompt for this one:

Admittedly no, this one took a whopping 14 generations to get it perfect, with me tweaking the prompt. The main issue was that the train didn't look like it was moving fast enough.

Eventually I realized that instead of prompting for a fast train, describing the environment as rushing by, motion blur, etc worked better. Got there eventually!

You can see my full prompt for this one here:

@reidhannaford This is incredible. How does Seedance know who is who? Do you designate some type of color marker for the shapes so it knows X shape/color = X character, etc.?

@Vitaliy682183 If you want the same character or object to appear consistently across different shots, you need to create a reference sheet and include it in your generation. Seedance 2.0 is multi-modal and you can upload a number of references, including the start frame, motion ref, etc

@reidhannaford this largely describes how I see the direction of many creative fields going

@magneticskiff Yeah I actually find the less detail the better sometimes, so Seedance doesn't get confused. The blockout is really just for spatial reference.

Reid, this is all really cool - I've been messing a bit a Blender/Seedance work flow as well. I've been trying to find good ways to create the additional frames I need, you need good starter frames per shot and this tends to work really well. I had been doing more complicated blender mockups though and it's awesome to see how much easier I can probably make it. Thanks for sharing.

@martinleblanc Posted the full prompt here:

@reidhannaford I wonder if we could use Claude opus 4.8 to write hyperframes scene reference using threejs and use it as reference. I know the whole point of using blender is for more control. Great job btw It opens up so much possibilités like using geometry nodes to make dr strange like vfx.

@reidhannaford This is the way, VFX is truly getting disrupted

Seedance and Omni are right at the cusp of the quality to make this approach viable

@reidhannaford This is awesome! I’ve been using VirtuCamera2 to do the same but it’s a bit hard to calibrate, any tips there?

@reidhannaford the 'directing vs describing a shot' line is the whole shift in one sentence. blockout as spatial reference is clever

@reidhannaford How do you/it deal with special geometry like a specific model of spaceship/environment etc. I'm trying to wrap my brain around shot consistency.

I guess you could model the thing and then train the AI model on it???

Blender can feel pretty intimidating for beginners but it's definitely doable! I would start with the basics and try to understand how the 3D viewport works and how to move shapes around.

Then you need to understand how keyframes work to animation the camera. That's really all you need for this workflow.

@reidhannaford 1. Generate a start 〜 ☝️ What prompt are you giving to Midjourney? You specify the first image, set the image parameters , and what about the numerical values, like --iw 2.0?

I tried generating a start frame image in Midjourney the same way, but the composition was way off. 😭

@reidhannaford this is cool, but how long does it take to do the shapes in blender?