Social Media Video Creator
End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.
Reads your brand identity, ICP, and messaging documents to produce on-brand social video — fully optimized for Seedance 2.0's instructional prompt grammar and your target platform.
Agent Execution Protocol
Step 1 — Read Brand Files
Before writing anything, the agent MUST read all available brand files. Look for them in the working directory or any brand/ subdirectory:
If a file is missing, proceed with what's available and note the gap.
Step 2 — Write the Social Post + Storyboard
Use brand context to produce:
Social Post Copy (for caption/copy):
- Hook line (first 1–2 sentences — must stop the scroll)
- Body (3–5 sentences: problem → solution → proof → CTA)
- Hashtags (5–8 relevant tags)
- CTA (one clear action)
Storyboard (match duration to platform spec):
Tone must match brand personality. If brand is playful → upbeat transitions, bright grade. If brand is premium → slow reveals, dark luxury aesthetic, moody lighting.
Step 3 — Craft the Seedance 2.0 Director Prompt
Transform the storyboard into a technical Director Brief for Seedance 2.0.
Rules:
- Never use vague descriptors ("beautiful", "amazing", "8k"). Use technical cinematography language.
- Always specify camera movement, lens type, and lighting physically.
- For 10s+ videos, use timecode segments:
0–3s: [...] 3–7s: [...] 7–10s: [...] - Integrate
@image1,@image2reference tags if images are provided. - Always include sound direction (even brief) — Seedance generates audio.
- Lead with composition, end with texture and micro-motion.
Director Brief Template:
Step 4 — Generate Reference Images (If Needed)
When to generate reference images:
Image generation — best models by use case:
Reference image prompt format: Write a clean, technical image prompt (not a Seedance prompt). Include:
- Subject description + key product/brand visual elements
- Lighting (studio, golden hour, etc.)
- Shot framing (medium shot, product close-up, etc.)
- Mood/color palette matching brand identity
- NO motion language (this is for a still frame)
Execute image generation:
Step 5 — Generate the Video
Choose mode, tier, and camera based on content type and available assets.
Mode selection:
Invoke the script:
Platform Specs
Tier note: Use
--tier globalor--tier vipfor1:1and21:9formats. Chinese tier supports only 16:9, 9:16, 4:3, 3:4.
Camera Language Reference
Standard Camera Intents (--camera / --intent flags)
Specialty Camera Intents (New)
FPV Prompt Enrichment:
Drone Flythrough Prompt Enrichment:
Prompt Quality Checklist
Before finalizing the Seedance prompt, verify:
- Scene environment is physically specific (not "nice background")
- Camera movement named explicitly (dolly in, orbit, drone flythrough, FPV, etc.)
- Lighting described technically (volumetric god rays, rim lighting, soft diffused, etc.)
- Subject/product described with visual specifics from brand-identity.md
- Sound direction included (even one line)
- Timecodes used for 10s+ videos
-
@image1etc. referenced if images are provided - Brand CTA or tagline included in final seconds
- No vague adjectives ("amazing", "beautiful", "stunning") — replaced with technical terms
Example: Full Workflow
User: "Make an Instagram Reel for our cold brew coffee brand, drone shot, premium feel"
Step 1 — Brand read: Read brand-identity.md (minimalist packaging, dark roast, black + gold palette), ICP.md (urban professionals 25–40, values quality), messaging.md ("Precision Brewed. Zero Compromise.")
Step 2 — Storyboard:
Step 3 — Seedance Director Prompt:
Step 4 — Generate reference: google-imagen4-ultra → cold brew bottle product shot (9:16)
Step 5 — Generate video:
Common Mistakes to Avoid
- Reading brand files and ignoring them — the storyboard must visually match the brand palette and tone.
- Generic prompts — "a nice video of a product" produces generic output. Every token must direct.
- Wrong tier for aspect ratio — 1:1 and 21:9 require
--tier globalor--tier vip. - Forgetting sound — Seedance generates audio. Direct it, or you get random results.
- FPV with static subject — FPV requires continuous motion in the scene. Pair with movement-rich environments.
- Drone without establishing shot — drone works best when it resolves INTO something (a product, a scene, a subject).
- Too many scene changes in 5s — match complexity to duration. 5s = 1 beat. 15s = 3–4 beats.

