A lot of us are used to proprietary video models but open models are getting pretty good too. Take the LTX-2.3 model: it now offers sharper details when it comes to hair, text, edges, and textures. It also has less freezing and smoother motion for image to video. It offers tighter audio sync for text to video. This model is trained on vertical data, so it is ready for up to 1080×1920 videos.
LTX-2.3 is now live on OpenArt. 🎬
The most capable open video model just got a major upgrade and you can use it right now.
What’s new in 2.3:
→ Sharper fine detail: Hair, textures, text, edges. All of it.
→ Tighter prompt adherence: Complex multi-subject prompts? Handle it.… pic.twitter.com/oK9c8ZDlAI— OpenArt (@openart_ai) April 13, 2026
