Seedance2 Api
Turn a storyboard concept into Seedance 2.0 video with Seedream 4.5 reference images via MCP or a fallback Python script when MCP is down.
Overview
seedance2-api is an agent skill for the Build phase that runs storyboard-to-video generation through Seedream 4.5 images and Seedance 2.0 tasks with MCP-or-script execution.
Install
npx skills add https://github.com/hexiaochun/seedance2-api --skill seedance2-apiWhat is this skill?
- End-to-end flow: storyboard → reference images (Seedream 4.5) → Seedance 2.0 video task → poll results
- Dual execution: MCP (`submit_task` / `get_task`) with automatic fallback to Script Mode
- Configurable aspect ratio and duration on video submission
- Script mode uses bundled `scripts/seedance_api.py` plus `XSKILL_API_KEY` and `requests`
- Text-to-image and image-editing paths for reference frames before video
- Dual modes: MCP tools and standalone Python script
- Pipeline stages: storyboard, reference images, video task, results
Adoption & trust: 11.5k installs on skills.sh; 0/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a storyboard or concept but no repeatable agent workflow to generate reference frames and submit Seedance 2.0 video jobs when MCP may be offline.
Who is it for?
Solo builders automating short AI video clips and reference stills inside Claude Code or Cursor with xskill credentials.
Skip if: Teams that need non-xskill providers, fine-grained timeline editing in NLE software, or video generation with zero external API keys.
When should I use this skill?
You need end-to-end AI video from a concept using Seedream 4.5 plus Seedance 2.0 and want MCP with script fallback.
What do I get? / Deliverables
You get reference images and a completed Seedance 2.0 video task result using either MCP tools or the bundled Python script after mode detection.
- Seedream 4.5 reference images
- Submitted Seedance 2.0 video task and retrieved output
Recommended Skills
Journey fit
Canonical shelf is Build because the skill’s job is producing media assets through external APIs, not distribution or ops. Integrations fits xskill-ai MCP tools and `seedance_api.py` script calls for image and video task submission.
How it compares
Use as a procedural integration skill for xskill Seedance/Seedream, not as a local FFmpeg or Runway desktop substitute.
Common Questions / FAQ
Who is seedance2-api for?
Indie creators and agent users who want scripted or MCP-driven Seedance 2.0 video from storyboards without writing custom API clients each time.
When should I use seedance2-api?
During Build when you need marketing clips or prototypes, during Validate when you storyboard a landing demo, or anytime you have `XSKILL_API_KEY` and a clear shot list.
Is seedance2-api safe to install?
It needs network access and an API key for xskill services; review the Security Audits panel on this page and treat keys as secrets in your environment.
SKILL.md
READMESKILL.md - Seedance2 Api
# Seedance 2.0 Storyboard & Video Generation End-to-end workflow from concept to final video: Storyboard → Reference images → Submit video task → Get results. ## Step 0: Determine Execution Mode (MCP or Script) **Check MCP availability first:** - Check `xskill-ai` MCP service status (read `mcps/user-xskill-ai/STATUS.md`) - If MCP is available → use `submit_task` / `get_task` and other MCP tools - If MCP is unavailable or returns errors → switch to Script Mode **Script mode prerequisites:** - Verify `XSKILL_API_KEY` environment variable is set (run `echo $XSKILL_API_KEY | head -c 10`) - If not set, prompt the user: ``` export XSKILL_API_KEY=sk-your-api-key ``` Get your API Key: https://www.xskill.ai/#/v2/api-keys - Verify `requests` is installed (`pip install requests`) **Script path:** Located under this skill's directory at `scripts/seedance_api.py`: ``` # Find via Glob tool glob: .cursor/skills/seedance2-api/scripts/seedance_api.py ``` In the following steps, each API call provides both MCP method and Script method. Choose one based on the Step 0 result. ## Step 1: Understand the User's Idea Collect the following information (proactively ask if anything is missing): - **Story concept**: one-sentence summary of the video - **Duration**: 4–15 seconds - **Aspect ratio**: 16:9 / 9:16 / 1:1 / 21:9 / 4:3 / 3:4 - **Visual style**: realistic / animation / ink wash / sci-fi / cyberpunk, etc. - **Assets**: existing images/videos/audio, or need AI generation - **Function mode**: first & last frame control (`first_last_frames`) or default omni mode (`omni_reference`) ## Step 2: Deep Dive (5 Dimensions) Guide the user through each dimension for richer detail: - **Content** – Who is the subject? What are they doing? Where? - **Visuals** – Lighting, color palette, texture, mood - **Camera** – Push in / pull out / pan / tilt / track / orbit / crane - **Motion** – Subject actions and pacing - **Audio** – Music style, sound effects, dialogue ## Step 3: Build Storyboard Structure Break down shots along the timeline using this formula: ``` [Style] _____ style, _____ seconds, _____ ratio, _____ mood 0-Xs: [Camera movement] + [Visual content] + [Action description] X-Ys: [Camera movement] + [Visual content] + [Action description] ... [Audio] _____ music + _____ SFX + _____ dialogue [References] @image_file_1 _____, @video_file_1 _____ ``` See `reference.md` for detailed templates and examples. ## Step 4: Generate Reference Images (If Needed) If the user has no existing assets, use Seedream 4.5 to generate character art, scenes, first/last frames, etc. ### Text-to-Image Call `submit_task` tool: - `model_id`: `fal-ai/bytedance/seedream/v4.5/text-to-image` - `parameters`: - `prompt`: detailed image description (English works best) - `image_size`: choose based on video aspect ratio - `num_images`: number needed (1–6) ```bash python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \ --model "fal-ai/bytedance/seedream/v4.5/text-to-image" \ --params '{"prompt":"An astronaut in a white spacesuit...","image_size":"landscape_16_9","num_images":1}' ``` ### Image Editing (Modify Existing Images) Call `submit_task` tool: - `model_id`: `fal-ai/bytedance/seedream/v4.5/edit` - `parameters`: - `prompt`: editing instructions (use Figure 1/2/3 to reference images) - `image_urls`: array of input image URLs - `image_size`: output size ```bash python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \ --model "fal-ai/bytedance/seedream/v4.5/edit" \ --params '{"prompt