AI, Design, and the Power of Open Models

**Mohammad Norouzi** (0:05)
It's not about how good a model is in the general sense. It's about how good is this model for my use case. For a lot of design and marketing use cases, we need editable design, not a single flat image.

**Justine Moore** (0:20)
It's super impressive, honestly, reaching the level of things like Nano Banana or GPT image with an open-source model. Why did you think that was important?

**Mohammad Norouzi** (0:27)
We really want our models to have taste. Every artist, they can really customize this model to the nuances of their style, the texture of their canvas, and really get 2K output, and hopefully make that part of their workflow.

**Yoko Li** (0:43)
One thing we were always wondering is that this release, open-source model is so small. It's 9.3 billion parameters. Like previously, a SOTA is probably like 80 billion parameters. It's like 9x of a difference. How did you do it?

**Mohammad Norouzi** (0:57)
We focused on...

**SPEAKER_4** (0:58)
Image generation has improved dramatically over the last few years. The next challenge is not simply creating images, but giving users more control over what gets created and how. That includes everything from typography and layouts, to editing, customization and workflows that fit into professional creative processes.
Yoko Li and Justine Moore speak with Ideogram founder and CEO, Mohammad Norouzi, about image generation, open weight models, design tools, and the future of creative AI.

**Justine Moore** (1:33)
So today we're excited to have Mohammad, CEO and founder of Ideogram, a Toronto-based generative AI company that just released their first open weight image model. Congrats on the huge release.

**Yoko Li** (1:44)
Thanks so much.

**Mohammad Norouzi** (1:45)
Thanks for having me.

**Justine Moore** (1:46)
We're really excited to talk through something that everyone has been buzzing about, which is the fact that the model is open weights. The previous Ideogram models have been closed source, so we'd love to hear how you made the call to make it open this time.

**Mohammad Norouzi** (1:59)
What has happened is there has been a lot of progress in the industry, and we used to do everything. Basically, we had our own first-party app as well as our own first-party API, and model development itself is a lot of work.
And we decided to focus a little more on the model side. I think that's where a lot of potential exists. We still want to continue to own the interaction with the users. I think there's a lot of important feedback we can get from the users directly. But then we want to focus more on building the model. And by releasing the weights, we're actually extending ourselves and working with inference providers, working more directly with large enterprise. They have every ability to customize the models or host it on-prem or optimize it for device.
And we would love to work with the best chipmakers to really optimize the model, the best inference providers. So this is basically us saying, hey, we are very serious about building the foundation model, and we would like to work with you wherever you are, whether you're an app developer or a chipmaker or an inference provider.

**Yoko Li** (3:14)
I think you already kind of touched on this. The new open-source model is very exciting in that it unlocks a lot of new use cases. It's very photorealistic. I think it can generate up to 2K, which is a smaller model too. Obviously, there's very precise layout control as well. Do you want to talk about some of the net new use cases that's unlocked by this model?

**Mohammad Norouzi** (3:34)
So this is actually a foundation based on which we're going to release some more exciting features next. So this is just the first release, we're just testing the waters, figuring out how to work with Hanging Face and the open source community, Comfy UI, etc. What I'm personally most excited about is something we haven't released yet, which is editable text and layout control.
And I really believe for a lot of design and marketing use cases, we need editable design, not a single flat image. And we haven't released that yet. We kind of showed the teaser in our video, but I'm personally most excited about that. On the technical side, what we've done is we went really detailed on the prompting.
And if you look at our prompts, it's like thousands of words, each element in the image, where it is in the image, we have layout control, bounding box and a number of elements. And that's one of the key innovations here that unlocks a lot of, again, design use cases because you clearly want font control, you want layout control. And this model is very versatile, allows you to really fix certain elements, fix positioning and control the image generation in every detail possible.