The alpha, twice a week
That was 3 min.
Get the best new moments in your inbox every Wednesday and Saturday. It's free.
Check your inbox
We sent a link to your address. Click it to finish signing up. Not there in a minute? Look in spam.
or
The TWIML AI Podcast · 3 min · Nov 10, 2026
Style mismatches can be fixed without retraining from scratch
Craft made cartoon images too realistic despite strong portrait results.
In this episode
Full analysis- 5:09Canva's data makes smaller design models more economical3 min
- 16:34Detailed scene descriptions help smaller models create better designs5 min
- 39:35Owning the model stack creates more room to cut inference costs4 min
- 10:58Layered designs let people move elements before regenerating pixels4 min
- 22:51Design editing needs benchmarks beyond single-shot generation4 min
- 27:04Style mismatches can be fixed without retraining from scratch3 min
- 31:14Brush revises designs through tools and visual feedback5 min
- 35:48A simpler agent harness lets the model use familiar code paths4 min
“the cartoon images generated with craft initially were a little bit too realistic and too 3D looking.”
Takeaways
- Portrait quality work left some cartoon images too realistic.
- Arena testing exposed the mismatch in style.
- Fine-tuning and RL can adjust style without repeating pretraining.
About this segment
Craft made cartoon images too realistic despite strong portrait results. Stefano Corazza says fine-tuning and reinforcement learning can correct style without repeating pretraining.
Stefano Corazza is head of AI research at Canva.
Sam Charrington, Host · Host, The TWIML AI Podcast
From “AI Design Still Feels Like a Slot Machine”, Nov 10, 2026. Watch the full episode
Thanks. We'll look at and fix what's off.
Transcript
Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.
- 27:08
we have seen for example the model perform really well on like portraits and people and also nature landscapes. We have seen the model doing not so great on the cartoon type of content for example. Is it not so great? I mean it's not ranking in the top three and so that's an area there. So like all that is together that is counterintuitive to me because um you know a portrait for example seems like it would kind of null the value of like the planning and the scene component like it's a portrait you know and a cartoon for example like you know you've got all these things in a cartoon you know that that would lean a lot on a a scene generating component.
- 28:00
But the two results that you're seeing suggest that that model shouldn't be as strong as it is or that that's not the source of the strength of the model, right? Am I thinking about that correctly? Yeah, it's interesting. So the number one thing for people in portraits that you want is basically to be as photorealistic as possible, right? Like you don't want to have that AI skin effect and all that stuff.
- 28:23
And we put so much effort in this because we were like, we got to nail it, it should not look like AI generated. I think that effort may have bled into the cartoon side where instead you weren't very stylized. And so it turns out that the images, the cartoon images generated with craft initially were a little bit too realistic and too 3D looking. But again, this is something that, you know, we discover when we put it on the arena because probably they had like a different population of designers that would test it.
- 28:59
But at the same time, it's something that is more about the taste of the model and that is a lot simpler, a lot easier, a lot faster to tune and correct. And so that we are in the process, basically, of doing exactly that. And, you know, tuning the taste of the model and the style of the model is more of a fine-tuning and RL type of task. You don't have to pre-train, right? In the pre-training, we, of course, had a lot of cartoon content.
- 29:29
Just now, that capability didn't surface to the full extent. And so now we are like teaching the model, okay, this is a style that resonates more with humans and we want, you know, if this cartoon is to be flat-shaded and these lines and so on, I mean, it's fascinating, honestly. It's a journey of learning. As much as the model is learning, we are learning how to train the model and how the model behaves.