Advanced video generation with Seedance 2.0
Seedance 2.0
The video features a male speaker, likely a host or presenter, delivering a speech or monologue. The overall mood is professional and engaging, set against the backdrop of a city skyline at what appears to be dusk or dawn. The setting is an outdoor rooftop with some greenery, implying an urban environment. The activity level is static, focusing on the speaker's delivery. The visual style is realistic and well-lit, with a clear focus on the subject. The emotional tone is confident and communicative. The speaker is a middle-aged man with short brown hair, wearing a dark suit jacket and a white collared shirt. The artistic style is photorealistic. The color characteristics are warm tones, with the sky displaying an orange and yellow gradient, contrasting with the cool grays of the city buildings. The color palette includes orange, yellow, black, white, and various shades of green and gray.
Seedance 2.0
The video features a male speaker, likely a host or presenter, delivering a speech or monologue. The overall mood is professional and engaging, set against the backdrop of a city skyline at what appears to be dusk or dawn. The setting is an outdoor rooftop with some greenery, implying an urban environment. The activity level is static, focusing on the speaker's delivery. The visual style is realistic and well-lit, with a clear focus on the subject. The emotional tone is confident and communicative. The speaker is a middle-aged man with short brown hair, wearing a dark suit jacket and a white collared shirt. The artistic style is photorealistic. The color characteristics are warm tones, with the sky displaying an orange and yellow gradient, contrasting with the cool grays of the city buildings. The color palette includes orange, yellow, black, white, and various shades of green and gray.
Multimodal video generation with synchronized audio
Generate videos from text, images, video clips, and audio references combined. Seedance 2.0 produces video and sound together in a single pass, with no post-production sync required.
Multimodal input
Combine text, up to 9 reference images, 3 video clips, and 3 audio clips in a single generation for precise creative control.
Audio-visual joint generation
Video and audio generated in one pass. Dialogue, music, ambient sound, and foley are synchronized from the start. Dual-channel stereo.
Reference-driven control
Supply reference images, videos, and audio to anchor visual style, camera movement, and pacing. The model preserves these across generation.
Complex motion and physics
Realistic multi-subject interactions, sports footage, crowd scenes, and choreography with physically plausible motion and detail.
Video editing and extension
Regenerate specific sections with new prompts and extend video length with continuous motion and consistent subjects.
Full production stack
Connect to Text to Speech, lip-sync, Eleven Music, AI Sound Effects, and Flows for end-to-end video production in one platform.
Create with Seedance 2.0 with full control
Create with Seedance 2.0 with full control
Select Seedance 2.0
Select Seedance 2.0 from the ElevenCreative model shelf to start generating video with synchronized audio.
Enter prompt and add references
Describe your scene with a text prompt and optionally add reference images, video clips, or audio to guide style and motion.
Generate and refine
Generate your video, then refine sections, extend length, or add narration, music, and sound effects in Studio.
Frequently asked questions
Get started with Seedance 2.0 for free
The best image, video, and audio models — all inside ElevenCreative. Start generating today.

Discover more image & video generation models
Explore our full library of AI image and video generation models, each with unique strengths and capabilities.
