People, every show

Andreas Blattman

Co-Founder, Black Forest Labs. On 1 show, 1 appearance. The Shows tab opens the full record on each.

founderscientistengineerLinkedIn ↗bfl.ai ↗

Andreas Blattmann is a co-founder of the generative AI company Black Forest Labs, best known for developing the FLUX foundation models. Previously an AI researcher at LMU Munich and Stability AI, he co-invented Latent Diffusion Models and co-developed Stable Diffusion and Stable Video Diffusion.

What they said4 Shows1

Everything Andreas Blattman said on any show that made the record, most notable first. Each card names its show and opens the statement there.

a16z What-if

Blattman: AI image progress depended on open-sourcing Stable Diffusion

“Open sourcing, like a foundation model as stable diffusion initially, that led to a whole lot of research on these models, which was, yeah, it was in, in retrospect, extremely important to do this. I think otherwise we wouldn't have seen the improvements we sa…”

Andreas Blattman Feb 17, 2024 ▶ 9:26 Text to Video: The Next Leap in AI Generation

a16z Insight

Blattman: Video AI models must learn physics and 3D geometry

“I think video is, is like an awesome kind of data because you, to solve that task, to solve video generation, a model needs to Learn much about like physical properties of the world of like the physical foundations of the world that there is so much without kn…”

Andreas Blattman Feb 17, 2024 ▶ 12:01 Text to Video: The Next Leap in AI Generation

a16z Insight

Blattman: High batch sizes are critical for training diffusion models

“So for diffusion models, it's really important to have a high batch size, because the gradients gets, like, you can approximate the gradient, which thrives the learning much better if the batch size is higher. And especially for diffusion models, it's like rea…”

Andreas Blattman Feb 17, 2024 ▶ 17:43 Text to Video: The Next Leap in AI Generation

a16z Assertion Supported

Blattman: Stable Video Diffusion acquired 3D reasoning within 2,000 iterations

“We showed that by our three D fine tuning. This was, by the way, this was completely surprising for me seeing that model after a 1002 thousand iterations, like already getting what is like, three D reasoning or like explicit three D reasoning.”

Andreas Blattman Feb 17, 2024 ▶ 29:27 Text to Video: The Next Leap in AI Generation

One line per show, most statements first. The link opens Andreas's full record on that show: the calibration, argument clarity, speaking style and every statement made there.

Show	Role there	Eps	Statements	Record
a16zLEDGER	Co-Founder, Black Forest Labs	1	4	100% 1/1	full record on the a16z Podcast →