Yes, even with seedance 2.0 running ahead, the fact that we have these models locally at this quality right now shows the gap is indeed closing fast. I see some incredible stuff around the internet
@linusekenstam
-
Download or clone repo for open source video and audio model
By
–
You can download now, or clone the repo, explore the bleeding edge of Open Source and Audio model from @ltx_model
-
Workflow: one photo to multiple angles cinematic video
By
–
Workflows that you might be used to with closed source models, like nanobanana pro etc can now be achieved through mixing different providers.
— Linus ✦ Ekenstam (@LinusEkenstam) 14 février 2026
Here us an example of:
One photo → multiple camera angles → cinematic video
video from: @FloyoAI pic.twitter.com/0pbcZIyDP4Workflows that you might be used to with closed source models, like nanobanana pro etc can now be achieved through mixing different providers. Here us an example of: One photo → multiple camera angles → cinematic video video from: @FloyoAI
-
Combining Seedance 2.0 with LTX-2 dubbing for borderless content
By
–
You can also combine things like Seedance 2.0 with LTX-2 dubbing.
— Linus ✦ Ekenstam (@LinusEkenstam) 14 février 2026
Then you get something like this, content knows no borders.
from @antonch44379293 pic.twitter.com/l0Aojr0zZEYou can also combine things like Seedance 2.0 with LTX-2 dubbing. Then you get something like this, content knows no borders. from @antonch44379293
-
Guide to Comfy + LTX-2 setup with example and resources
By
–
My buddy @techhalla has also done some very good dives into how to get setup with Comfy + LTX-2
— Linus ✦ Ekenstam (@LinusEkenstam) 14 février 2026
Here is both an example of what you can create, but in his thread he also links to good resources he put together on getting started.https://t.co/wllkqdcmxGMy buddy @techhalla has also done some very good dives into how to get setup with Comfy + LTX-2 Here is both an example of what you can create, but in his thread he also links to good resources he put together on getting started.
-
LTX-2 Open-Source Model with 3.3M Downloads in a Month
By
–
+3.3 Million downloads in 1 Month 🔥
— Linus ✦ Ekenstam (@LinusEkenstam) 14 février 2026
Yet most people are sleeping on LTX-2 plus the fact that its Open-Source
That's right, you can even run it at home, at the cost of electricity.
Let's dig into why I think you should spend some time with this model.
🧵 A thread pic.twitter.com/GHP4syswyQ+3.3 Million downloads in 1 Month Yet most people are sleeping on LTX-2 plus the fact that its Open-Source
That's right, you can even run it at home, at the cost of electricity. Let's dig into why I think you should spend some time with this model. A thread -
Linus Ekenstam: AI is math, not sentient or stealing
By
–
The amount of people here that skipped 1st grade algebra is astonishing. reckon they all did well in arts. ML/AI is maths, computers simply breaking down everything into numbers and for human brains to do the same, we need to be savants, AI is not stealing, AI is not sentient
-
Have you run local generative AI on your own hardware?
By
–
Have you run local generative AI models on your OWN hardware?
-
Distinguishing proper LLM book writing from chatbot copy-paste
By
–
You would not know if you read a book written by an LLM if it was done right. copy/paste in a chatbot is not writing a book with an LLM. but you seem to distracted from knowing or understanding that.
-
Seedance 2.0 world understanding compared to Nanobanana Pro
By
–
yes, accurate, very sloppy prompt, the world understanding capacity of seedance 2.0 seems on par with nanobanana pro