Vidu 1.5
Vidu 1.5 is an advanced video generation model developed by Shengshu Technology, released on November 13, 2024. This version builds upon its predecessor Vidu 1.0, introducing more advanced features that enhance the quality and consistency of generated videos. Try Vidu 1.5 below!
Key Features of Vidu 1.5
- Consistent Character Video Generation: Create videos with multiple-entity Consistency and multiple-angle Consistency.
- Advanced Control Over Cinematography: Flexible control over camera movements and angles.
- Improved Detail Generation: Enhanced details with elements rendered more actually
- Expanded Animation Styles: Various styles you can generate with Vidu 1.5
- Enhanced Semantic Understanding: More flexible and accurate prompt control
🚀 Ready to Create with Vidu-1.5? Check Out the Latest Update! 🚀
— Vidu AI (@Viduforhuman) November 21, 2024
We’re excited to share a sneak peek of Vidu-1.5 in action! 🎥 With enhanced Multi-Entity Consistency, you can now create even more realistic and dynamic videos, blending people, objects, and environments like… pic.twitter.com/PVDkWlAseB
Consistent Character Video Generation
Vidu 1.5 introduces advanced consistent character video generation capability for its Reference to Video feature. This overcomes a common challenge in generative video production where character traits can blend or become inconsistent.
🚀 Introducing Vidu: A New Era for Multimodal AI 🚀
— Vidu AI (@Viduforhuman) November 13, 2024
We’re thrilled to announce the launch of Vidu-1.5, the world’s first multimodal model with Multi-Entity Consistency!🎉
With Vidu-1.5, you can now seamlessly integrate people, objects, and environments to create stunning… pic.twitter.com/uLOrE3Zcz4
Multiple-Entity Consistency
This innovative capability allows users to integrate unrelated images—such as people, objects, and environments—into a cohesive video. This feature ensures that distinct attributes of each entity remain consistent throughout the video.
|
|
Multiple-Angle Consistency
Vidu 1.5 can also generate videos from multiple angles by accepting up to three images of a subject taken from different perspectives. Vidu 1.5 maintains visual continuity across these angles, providing a natural 360-degree view of the subject while accurately reproducing facial expressions and movements.
Advanced Control Over Cinematography
Vidu 1.5 enhances user control over camera movements and angles, allowing for dynamic adjustments such as zooming, panning, and tilting within the generated footage. This level of control enables creators to implement sophisticated cinematic techniques without compromising visual consistency.
Improved Detail Generation
The model boasts enhanced detail generation capabilities, producing videos with clarity up to 1080p resolution. This improvement allows for intricate visuals, such as textures and patterns, to be rendered more accurately, enriching the storytelling experience.
Examples |
Expanded Animation Styles
Vidu 1.5 caters to a broader audience by including new video styles, such as oil painting, claymation, Japanese fantasy and hyper-realistic aesthetics. This expansion makes it suitable for both casual creators and professional filmmakers looking for polished outputs.
Style | Video |
Vincent van Gogh | |
Pop Art | |
Steampunk | |
Claymation |
Text to Video with Enhanced Semantic Understanding
The model leverages advanced semantic understanding to interpret complex text prompts more effectively than previous versions. This capability reduces manual post-production efforts by up to 50%, allowing for smoother transitions and more cohesive storytelling.
Prompt | Video |
In classical romantic movie style (film style/shooting methodology), a teddy bear, dressed in rugged Western attire with a wide-brimmed hat and a bandolier, gazes at the camera, its lips trembling slightly as it exhales a puff of smoke. The warm glow of its cigarette illuminates faces, casting shadows that emphasize its somber mood. Its paws rest on the porch railing in a relaxed pose, but its button eyes betray a deeper sadness. As it slowly turns its head to the left, its gaze shifts to the distant horizon, lost in thought. The lighting is soft, with a blend of pink and golden hues from a setting sun, enhancing a romantic atmosphere. The setting, a porch with wooden panels and a window behind it, completes the Western ambiance, capturing a moment of introspective solitude amidst the vast open landscape. | |
A melancholic teddy bear, dressed in rugged attire with a wider-brimmed hat and a bandolier, gazes at the camera, its lips trembling slightly as it exhales a puff of smoke. The warm glow of its cigarette illuminates its face, casting shadows that emphasize its somber mood. Its paws rest on the porch railing in a relaxed pose, but its button eyes betray a deeper sadness. As it slowly turns its head to the left, its gaze shifts to the distant horizon, lost in thought. The lighting is soft, with cool blue tones contrasting the warm light from the cigarette, enhancing the mood of quiet reflection. The setting, a porch with wooden panels and a window behind it, completes the Western ambiance, capturing a moment of introspective solitude amidst the vast, open landscape. | |
Capture a serene moment featuring a baby Corgi swimming gracefully in a large, sunny pool. The underwater perspective showcases the puppy, its gentle smile illuminated by soft, golden hour lighting that filters through the water, creating a dance of light and shadow on the pool's bottom. The scene is set in soft pastel colors, enhancing the dreamlike, ethereal quality of the atmosphere. The high-resolution photography captures every delicate detail of the water's texture and the Corgi's joyful expression, creating a simple yet cinematic portrait of tranquility and innocence. This minimalist yet emotive setup conveys a sense of calm and happiness, ideal for a serene and visually captivating film sequence. |
Vidu 1.0 vs Vidu 1.5
Vidu 1.0 | Vidu 1.5 | |
Output resolution | Up to 720p | Up to 1080p |
Output length | 4s/8s | 4s/8s |
Consistent Character Video | Single character only | Multiple characters supported |
Movement Amplitude Control | ||
Aspect Ratio Control |
Vidu 1.5 YouTube Video Reviews
What People Are Talking About Vidu 1.5 on X
I did this clip only with Vidu 1.5 and it's probably one of the best tools available today to have consistent characters... If you can, try it: Vidu1.5#ViduAI #ViduChallenge #MultiEntityConsistency pic.twitter.com/6gbHz9myQ7
— RoyalKongZ (Laurent) (@RoyalKongz) November 17, 2024
Vidu:
— Naegiko | AI Animator (@naegiko) December 3, 2024
settings (v 1.5, Resolution: 1080p, Movement Amplitude: Auto, Duration: 4s)
prompt: A young person with short hair and a yellow backpack stands on the large hand of a giant stone creature. The creature has glowing red eyes and is partially covered in moss and vegetation.… pic.twitter.com/BppyO2VAiB
Vidu:
— Naegiko | AI Animator (@naegiko) December 3, 2024
settings (v 1.5, Resolution: 1080p, Movement Amplitude: Auto, Duration: 4s)
prompt: A young person with short hair and a yellow backpack stands on the large hand of a giant stone creature. The creature has glowing red eyes and is partially covered in moss and vegetation.… pic.twitter.com/BppyO2VAiB
Lastly: Vidu 1.5. I wanted to test the shiny new 2.0 model, but as of now, it doesn’t support text-to-video. Quality here? Not the best! Prompt adherence is okay but far from the best. The reflection falls apart, and the woman jumps around weirdly in the frame. Not great—maybe… pic.twitter.com/3pcZBLZTIZ
— Pizza Later (@Pizza_Later) January 17, 2025
Vidu AI 1.5 just introduced a new “Reference to Video” feature, and it’s interesting!
— el.cine (@EHuanglu) November 20, 2024
With this update, @Viduforhuman lets you upload two reference images to generate a video.
For this example, I used an image of a woman and a Coca-Cola bottle, and the results are super… pic.twitter.com/HIhwDsi5Jy
Vidu-1.5 from @Viduforhuman is out now! Here’s an example of the new Multi-Entity Consistency feature https://t.co/cphGG01ERe pic.twitter.com/BNOyFG0k4F
— William Lamkin (@WilliamLamkin) November 14, 2024
"Vidu-1.5 can seamlessly integrate people, objects, and environments to generate stunning videos, overturning traditional single-point fine-tuning methods like Lora."
— Chubby♨️ (@kimmonismus) November 9, 2024
Love to see how AI-Videos are accelerating!pic.twitter.com/cM6fPcKO3x
FAQs
How fast can Vidu 1.5 generate videos?
Vidu 1.5 can generate a four-second video clip in approximately 25 seconds, making it significantly faster than previous versions and other generative AI platforms.
Can I use Vidu 1.5 for different types of content?
Yes, Vidu 1.5 is versatile and can be used for various applications, including art design, game development, film post-production, and social media content creation.
Can I customize the generation of Vidu 1.5?
Yes, users can customize how Vidu 1.5 generates the videos, including customizing the prompt, style, video duration, resolution, movement amplitude and aspect ratio.
Is Vidu 1.5 free to use?
Yes, you can use Vidu 1.5 for free to generate limited videos. To generate more videos, you need to subscribe to a paid plan.