The Next Frontier of AI Video Is Control

Gorkem Yurtseven (0:00)

Generative media app is along with the coding agent market. What we call is token market fit. Everyone's waiting for a large consumer moment in AI.

I believe H3 Max makes it possible.

Jennifer Li (0:14)

Were you surprised by the speed up and the gain you could get from post-training this model?

Batuhan Taskaya (0:20)

We have a version called H3 Max Turbo that's public, that can generate like a five-second video in like 1.5 seconds. From a cost standpoint, it's also like 2x less.

Gorkem Yurtseven (0:29)

People are starting creating these beautiful scenes using an LLM model GPT Astra in Blender and all of a sudden it unlocked the whole new workflow for Hollywood and professional people.

Batuhan Taskaya (0:42)

We have been very focused towards speed, performance, quality, and now we have a really good pace model. The next month or two is going to be fully focused on.

Eric Torenberg (0:50)

What happens when AI video becomes fast enough to generate in real time?

A16Z general partner Jennifer Li sits down with FAL co-founder Gorkem Yurtseven and head of engineering Batuhan Taskaya to discuss H3 Max and the rapidly changing generative video stack. They unpack how post-training and systems optimization made video generation significantly faster, opening up new experiences where video can run continuously, remember previous scenes, and respond to direction as it plays. But speed is only part of the story. They also discuss the push toward greater control over camera angles, lighting, characters, and motion, and why those tools could make generative video more useful for professional creative workflows.

Jennifer Li (1:35)

Welcome Gorkem, Batuhan, to our podcast again. We did the last one last year. This is long overdue, and we have such an exciting model to talk about, which is Thal's H3 Max. The day when it came out, I was calling it, it's really in the league of its own. Like, it's so funny to see the benchmarks where you have the dot of this model on the far left or far right, and then everything else is on the other half.

Gorkem Yurtseven (1:57)

And that graph is actually log scale. It's actually further, but we had to fit it in. We had to do log scale.

Jennifer Li (2:04)

That is hilarious.

Gorkem Yurtseven (2:05)

The time portion, the quality is not.

Jennifer Li (2:08)

For sure. The internet noticed, for sure. There are so many viral tweets about it. Like, people really played around with this model.

Maybe just give us the back story of what inspired you to post train this open weight model from MiniMax. And how did you get the quality and speed to where it is?

Gorkem Yurtseven (2:26)

First of all, the MiniMax H3 model is the first truly open source, very capable, like, latest generation video model out there. So even though we worked with some of the other model labs to run inference for them, we never had this capability. Like, had the right to add this capability on top of it. So MiniMax came up with their very capable open source model that is truly last generation, can take references, like very familiar architecture to any other video model. We thought this is a great opportunity to go all in and see what we can do. And again, we did, like, many different things that we are going to talk about that combined gave the results that you show on the graphs.

But the biggest reason why everything came together for this particular moment was because H3 was the first truly next generation video model that's open source.

Jennifer Li (3:21)

What is the idea, given like FALL has been known to be like a general media inference serving platform, like what is the idea to get into post-training open-weight model? Like you talk quite a bit about it in the blog of like combining the system work with the model itself. Maybe talk more about the work behind that.

Gorkem Yurtseven (3:38)

Generative media is, I would say, along with the coding agent market, what we call is token market fit.

The way we define it is as, can a single person productively spend a lot of tokens? The amount is like 10k a month, something like that.

There is incredible amount of demand in the market to generate video, to generate many things at the same time. And a person who is doing this for their daily job, they spend in front of a computer and do this all day long, and they spend thousands of dollars, lots of tokens. And since around April, the whole industry and file itself, we've been compute constraint. We are growing as much as we are adding compute. Like there are things we do here and there, but the whole industry has been compute constraint. And we've always been looking for efficiencies where we can leave that a little bit so people can use this more. So that has been the idea behind everything we've been doing since April. And this just came at the right time because this makes everything maybe an order of magnitude more efficient. So it gives more compute for other models or even like more tokens can be generated using H3 Max. I think Batuhan would agree on that.