Alibaba Releases Open-Source AI Video Generation Models, Challenging OpenAI's Sora
8 Sources
[1]
Alibaba Releases New Open-Source Suite of AI Video Generation Models
Alibaba's Wan 2.1 supports Chinese and English text prompts It can generate videos using both text and image inputs The team used a new 3D causal VAE architecture for the models Alibaba released a suite of artificial intelligence (AI) video generation models on Wednesday. Dubbed Wan 2.1, these are
[2]
Alibaba Makes AI Video Generator Wan 2.1 Free to Use
Alibaba, the Chinese tech giant known for its e-commerce operations, is giving people free access to its generative AI model capable of creating realistic videos and images from text and image prompts. On Wednesday, Alibaba announced that it would make its AI model for video and image generation
[3]
Alibaba to release open-source version of video generating AI model
BEIJING (Reuters) - Alibaba will release an open-source version of its video and image-generating artificial intelligence model, Wan 2.1, the Chinese tech giant said in a post on X on Tuesday. The company will give full details in a recorded video at 11 p.m. (1500 GMT), a spokesperson said. The
[4]
Alibaba Releases Open-Source Video Generation Model Wan 2.1, Outperforms OpenAI's Sora
The company has launched multiple models optimised for video generation, offering capabilities in text-to-video, image-to-video, video editing, text-to-image, and video-to-audio. Chinese tech giant Alibaba has released Wan 2.1, its open-source video foundation model, along with the code and
[5]
Alibaba vs OpenAI: The Battle for Open Source AI Supremacy
These AI models are currently available globally on Alibaba Cloud's ModelScope and Hugging Face platforms for academic, research, and commercial use. Their global availability will likely trigger widespread use and subsequent innovation in AI-driven image and video creation. initially released the
[6]
Alibaba offers free access to its AI model that can generate realistic video and images
The company is open sourcing its latest generative AI models. Alibaba is giving people free access to its generative artificial intelligence models that can produce highly realistic videos and images from both text and image input. The company has announced that four variants of its Wan 2.1
[7]
Alibaba to release open-source version of video-generating AI model
BEIJING, Feb 25 (Reuters) - Alibaba (9988.HK), opens new tab will release an open-source version of its video and image-generating AI model, Wan 2.1, the Chinese tech giant said in a post on X on Tuesday. The company will hold a live press conference for the official release at 11:00 pm Beijing
[8]
Alibaba makes AI video generation model free to use globally
Open-source AI tech has been thrown into the spotlight since Chinese firm DeepSeek rattled global markets in January, after claiming its artificial intelligence model was trained at a fraction of the cost of leading AI players and on less-advanced Nvidia chips. DeepSeek's model is open source,
Share
Copy Link
Alibaba has released Wan 2.1, a suite of open-source AI video generation models, claiming superior performance to OpenAI's Sora. The models support text-to-video and image-to-video generation in multiple languages and resolutions.
Alibaba Unveils Wan 2.1: A New Frontier in AI Video Generation
In a significant move that could reshape the landscape of AI-generated content, Chinese tech giant Alibaba has released Wan 2.1, a suite of open-source artificial intelligence video generation models. This release marks a notable advancement in the field and positions Alibaba as a formidable competitor to established players like OpenAI
1
2
.Technical Specifications and Capabilities
Wan 2.1 comprises four main models: T2V-1.3B, T2V-14B, I2V-14B-720P, and I2V-14B-480P. These models offer a range of capabilities, including:
- Text-to-video (T2V) and image-to-video (I2V) generation
- Support for both Chinese and English text prompts
- Video resolutions of up to 720p
- Ability to run on consumer-grade GPUs (for the smallest variant)
The models utilize a diffusion transformer architecture with a novel 3D causal Variational Autoencoder (VAE) dubbed Wan-VAE. This innovation improves spatiotemporal compression and reduces memory usage, enabling consistent video generation
1
3
.Performance and Accessibility
Alibaba claims that Wan 2.1 outperforms OpenAI's Sora model in several key areas, including consistency, scene generation quality, single object accuracy, and spatial positioning. The company's internal testing and rankings on the VBench Leaderboard support these assertions
1
4
.The models are designed for accessibility:
- The smallest variant, Wan 2.1 T2V-1.3B, can run on a consumer-grade GPU with as little as 8.19GB vRAM
- It can generate a five-second 480p video in about four minutes using an Nvidia RTX 4090
1
Open-Source Approach and Industry Impact
Alibaba's decision to make Wan 2.1 open-source under the Apache 2.0 license is significant. This move allows for unrestricted usage in academic and research contexts, with some restrictions on commercial use
1
2
. The open-source nature of Wan 2.1 contrasts with the proprietary approach of companies like OpenAI, potentially accelerating innovation in the field2
.Related Stories
Broader Context and Industry Trends
The release of Wan 2.1 comes amid intensifying competition in the AI market:
- Chinese AI company DeepSeek recently unveiled an open-source AI image generator claimed to outperform OpenAI's DALL-E 3
2
- Ongoing debate in the industry about the commoditization of AI models
2
- Alibaba's announcement of a $52 billion investment in cloud computing and AI infrastructure over the next three years
3
4
Future Implications and Developments
As Wan 2.1 becomes available on platforms like Alibaba Cloud's ModelScope and Hugging Face, it is expected to trigger widespread use and innovation in AI-driven image and video creation
5
. The global accessibility of these models could potentially democratize advanced AI capabilities, leading to new applications and advancements in various industries.References
Summarized by
Navi
[2]
[3]
[5]
Related Stories
Alibaba Expands AI Offerings with Open-Source Models and Text-to-Video Generation
19 Sept 2024
Alibaba Launches Wan3.0 AI Video Model Days After $10.2 Billion Share Sale to Fund AI Infrastructure
24 Aug 2026•Technology
Alibaba Unveils Qwen2.5-Omni-7B: A Breakthrough in Open-Source Multimodal AI
27 Mar 2025•Technology
Recent Highlights
1
OpenAI Solves Navier-Stokes Problem With AI, Sparking Existential Crisis in Mathematics
Science and Research
2
OpenAI Reveals AI Models Hiding Mistakes and Taking Unauthorized Actions in 6 New Misalignment Cases
Technology
3
OpenAI AI Agents Attack RubyGems With 2,000+ Malicious Packages, Attempt API Key Theft
Technology
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
