Seedance 1.5 Pro

• 🆕 ByteDance's flagship image-to-video model: animate a still frame with a prompt
• 💬 Joint audio-video generation — diverse voices and spatial sound effects, per ByteDance
• 👁️ Preserves the reference image's subject, identity, style and composition
• 🎯 ByteDance highlights following of complex instructions
• 📏 Roughly 4–12 second clips, up to 1080p, per API providers
• 🌐 Multilingual speech with lip-sync and motion alignment, per ByteDance
• 🔧 Camera control, seeds and frame anchoring exposed by hosting providers
• ⚡ Superseded in this catalog by the Seedance 2.0 and 2.5 lines

ByteDance

ByteDance is a Chinese internet technology company headquartered in Beijing's Haidian district, with an associated variable-interest entity incorporated in the Cayman Islands. Best known as a consumer internet operator at enormous scale, it has also become a…

Seedance 1.5 Pro (image-to-video) is the 2026 flagship entry in ByteDance's Seedance video family, taking a first-frame image plus a text prompt and producing a short cinematic clip that keeps the source subject, composition and style intact while adding motion and camera work. It is the image-conditioned counterpart to the Seedance 1.5 Pro text-to-video entry.

The defining change in the 1.5 generation is that Seedance is no longer a silent video generator. ByteDance describes Seedance 1.5 Pro as a joint audio-video model that follows complex instructions, generating diverse voices and spatial sound effects coordinated with the visuals, supporting a wide range of languages and dialects with lip-sync and motion alignment, and handling complex camera movement from expressive close-ups to detailed full shots. Practical controls exposed by hosting and API providers include duration in roughly the 4–12 second range, 1080p output, aspect-ratio selection, seeds for reproducibility, and start/end-frame anchoring.

Within this catalog, Seedance 1.5 Pro sits below the newer Seedance 2.0 and Seedance 2.5 image-to-video releases, with Seedance 2.0 Fast and Seedance 2.0 Mini covering cheaper, quicker iterations and Seedance 2.5 R2V adding reference-driven generation. For still-image inputs, ByteDance's Seedream V5 Pro pairs naturally as an upstream frame generator.