Creative Claw — Seedance 2.5

Read shared execution guidance once per task before using tools. It covers existing authorization, model discovery, optional cost checks, imports, and recovery.

Use video/seedance-2.5 for long, premium, reference-rich generation with native synchronized audio. Prefer it when the clip needs more references, more duration, a controlled destination frame, or richer scene direction than the default video route.

Core workflow

1. Define the deliverable, duration, ratio, shot count, subjects, continuity, audio, and reference roles.
2. Search for existing assets and import every external image, video, or audio file into Creative Claw.
3. Reuse supplied/approved references. Create storyboards only for requested planning or unresolved visual continuity; do not add a storyboard gate to a clear single-clip request.
4. Create an end frame when the clip needs a precise landing pose, transition, loop, reveal, or match cut.
5. Call get_model_params({ model: "video/seedance-2.5" }). Runtime values override remembered limits. For reference-to-video, choose extras.omni_reference_task_type deliberately rather than relying on prompt inference for edits or extensions.
6. Assign every reference a written role and cite it with the exact @ImageN, @VideoN, or @AudioN token.
7. Set agentic_prompting: false for authored tokens, exact dialogue, timecodes, or precise shot plans.
8. Honor requested resolution directly. Use a lower-resolution proof only when the user wants drafts or has authorized that iteration workflow.
9. Inspect the output before merging it into a sequence.

Current model contract