Video Block

Video block enables dynamic storytelling, temporal exploration, emotional resonance, and immersive narrative construction. It bridges movement and sound, allowing you to craft experiences that evolve over time, engage viewers emotionally, and convey complex ideas with fluid transitions. Video blocks provide a canvas for experimenting with pacing, rhythm, and atmosphere, enabling layered storytelling that unfolds with intention. They invite interactivity and viewer interpretation, enhancing narrative depth through motion, soundscapes, and sequential imagery.

Here is a quick introduction on how to get started with video block!

Models

Video Models

Models	Modality	Description	Best For	Supported Parameters
Hailuo Minimax	Text to Video	Advanced multimodal model with strong contextual understanding. Good at interpreting complex prompts and maintaining narrative consistency.	Long-form videos with detailed storylines and character continuity.	/
Veo 2	Text to Video	Google's Veo2's text-to-video model offers high cinematic quality and dynamic motion. It excels in rendering smooth transitions and diverse motion dynamics but may struggle with scene coherence in complex scenarios.	Creating cinematic videos with realistic motion and high-quality output.	Aspect Ratio: Landscape(16:9), Portrait(9:16). Duration: 5s, 6s, 7s, 8s.
WAN 2.1	Text to Video	An Alibaba's open-source video generation model, available in 14 billion and 1.3 billion parameter versions. It supports text-to-video, image-to-video, and video editing tasks.	Creating videos with specified motion paths from images.
Kling 2.0	Text to Video, Image to Video.	Offers cinematic-grade video generation with complex camera movements like zooms and pans. Supports mixed image-text-video inputs and over 60 artistic styles.	Creating cinematic videos with complex camera movements and mixed inputs.	Aspect Ratio: Landscape(16:9), Portrait(9:16), Square (1:1).
Kling Standard 1.6	Text to Video	Balanced model focused on quality-to-speed ratio. Offers good visual fidelity with reasonable generation times.	Quick prototyping and general-purpose video creation with moderate detail requirements.	Duration: 5s, 10s.
Kling Pro 1.6	Text to Video	Specializes in photorealistic rendering with advanced lighting and physics simulation.	Product demos, architectural visualizations, and realistic human movements.	Duration: 5s, 10s.
Luma Ray 2	Text to Video, Image to Video.	A large-scale video generative model capable of creating realistic visuals with natural, coherent motion.	Generating realistic videos with coherent motion from text and images.	Aspect Ratio: Landscape(16:9, 4:3), Wide Landscape(21:9), Portrait(9:21, 9:16, 3:4). Resolution: 540p, 720p, 1080p. Duration: 5s, 9s. Loop: Yes/No.
Luma Ray 2 Flash	Text to Video, Image to Video	A variant of Luma Ray 2 model optimized for faster and more cost-effective generation.	Quick generation of short, realistic videos.	Aspect Ratio: Landscape(16:9, 4:3), Wide Landscape(21:9), Portrait(9:21, 9:16, 3:4). Resolution: 540p, 720p, 1080p. Duration: 5s, 9s. Loop: Yes/No.
Pika	Text to Video	Great for character animation and emotional expression. Good at maintaining consistent subjects across scenes.	Character-driven narratives, explainer videos with avatars, and emotional storytelling.	Aspect Ratio: Landscape(16:9, 3:2, 5:4), Portrait(9:16, 2:3, 4:5), Square(1:1). Resolution: 720p, 1080p. Duration: 5s, 10s. Loop: Yes/No.
Tencent Hunyuan	Text to Video	Largest open-source text-to-video model with 13 billion parameters. innovative video-to-audio synthesis for realistic sound generation.	Global marketing campaigns, localized content, and videos requiring cultural nuance.	Styles: None, 3D Character, Anime, Close-up; Resolution: 480p, 720p, 1080p; Pro Mode(Higher quality video generation): On/Off; Duration: 5s, 2.5s.
Lightricks LTXV	Text to Video	Good for maintaining smooth transitions between frames, reducing flickering and scene inconsistencies.	Generating dynamic video content quickly for storyboards and animatics with fluid scene transitions.	Quality (Increase the quality of the output): 0-100.