Motif Releases 2B Open-Source Text-to-Video Model
The new Apache 2.0 licensed model uses a diffusion transformer architecture to offer a new open alternative for video generation research.
Motif Technologies has entered the open-source video generation space with the release of Motif-Video-2B, a new 2-billion-parameter model. Available under a permissive Apache 2.0 license, it provides a new, accessible tool for creating short video clips from both text and image prompts.
The model is built on a diffusion transformer architecture, an approach that has gained significant traction in generative AI for its strong performance in modeling complex data. Unlike many high-profile video systems that remain proprietary, Motif has made the model weights and code publicly available through its Hugging Face repository.
Why it matters
The release of Motif-Video-2B contributes to a growing but still-nascent ecosystem of open-source video generation models. Its relatively modest 2B parameter size makes it more approachable for researchers and developers who may not have access to the massive computational resources required by state-of-the-art commercial systems. By providing a transparent and modifiable foundation, the model can help accelerate experimentation and innovation in the broader community.
Sources
- Visit
Motif-Technologies/Motif-Video-2B
Hugging Face
0 comments
No comments yet. Be the first to weigh in.
More in Text → Video
JD.com Enters Open-Source AI Video with JoyAI-Echo
The Chinese e-commerce giant has released a new model capable of generating long-form, multi-shot videos with synchronized audio from text prompts.
Baidu Releases NAVA for Text-to-Video with Audio
The new model from the Chinese tech giant uses a Multimodal Diffusion Transformer to generate synchronized audio and video from text or image prompts.
NVIDIA Releases SANA, a Camera-Controllable Video Model
The new model, SANA-WM, uses a bidirectional diffusion process to give creators fine-grained control over camera movement and video editing.