'Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.'
Installation
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
'Diagnose and fix failing or low-quality Seedance 2.0 prompts using a 5-step diagnostic tree. Use when a prompt is consistently failing, producing generic output, or being rejected. Covers blurry/jittery output, camera chaos, character drift, stiff action, and ambiguous results.'
seedance-troubleshoot · Diagnostic Tree (v5.0)
This skill diagnoses and fixes the most common Seedance 2.0 failure modes. It uses a simple diagnostic tree to identify the root cause and provides a specific, actionable solution.
The Diagnostic Tree
Start at the top and work your way down.
1. Is the output blurry, jittery, or morphing?
Root Cause: Overspecification. Your prompt is too long, has too many competing details, or too many actions in a short time (violating beat density).
Solution:
Cut the prompt length to 30-100 words.
Use a reference. Find an @Image or @Video that shows the style or action you want and replace 50+ words of description with a single @reference tag.
Simplify the action. Reduce the number of distinct movements in the shot.
2. Is the camera chaotic, spinning, or ignoring your instructions?
Root Cause: You have violated the One-Move Rule by stacking multiple camera moves in a single shot.
Solution:
Rewrite the camera instruction to include only ONE primary move (e.g., slow dolly push, handheld tracking, static wide shot).
If you need multiple moves, use the [Cut to:] syntax to create a sequence of shots, each with its own single move.
For complex moves, use a @Video reference and tell the model to Match the camera movement from @Video1.
3. Is the character not looking like your reference image?
Root Cause: The prompt is re-describing the character, which competes with and overrides the @Image reference.
Solution:
Delete all physical descriptions of the character from the prompt (hair color, clothing, face).
The prompt should only describe the character's action and emotion.
Ensure the @Image reference is a clear, well-lit shot of the character.
4. Is the action stiff, slow, or lacking impact?
Root Cause: Lack of intent and physics language. The model doesn't know how to perform the action.