seedance2-api

What this skill does

# 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:**

1. Check `xskill-ai` MCP service status (read `mcps/user-xskill-ai/STATUS.md`)
2. If MCP is available → use `submit_task` / `get_task` and other MCP tools
3. If MCP is unavailable or returns errors → switch to **Script Mode**

**Script mode prerequisites:**

1. Verify `XSKILL_API_KEY` environment variable is set (run `echo $XSKILL_API_KEY | head -c 10`)
2. 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
   ```
3. Verify `requests` is installed (`pip install requests`)

**Script path:** Located under this skill's directory at `scripts/seedance_api.py`:
```bash
# 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:

1. **Content** – Who is the subject? What are they doing? Where?
2. **Visuals** – Lighting, color palette, texture, mood
3. **Camera** – Push in / pull out / pan / tilt / track / orbit / crane
4. **Motion** – Subject actions and pacing
5. **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](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

<details>
<summary><b>MCP Method</b></summary>

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)

</details>

<details>
<summary><b>Script Method</b></summary>

```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}'
```

</details>

### Image Editing (Modify Existing Images)

<details>
<summary><b>MCP Method</b></summary>

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

</details>

<details>
<summary><b>Script Method</b></summary>

```bash
python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \
  --model "fal-ai/bytedance/seedream/v4.5/edit" \
  --params '{"prompt":"Change the background to a forest","image_urls":["https://..."],"image_size":"landscape_16_9"}'
```

</details>

### Poll Image Results

Images typically complete in 1–2 minutes.

<details>
<summary><b>MCP Method</b></summary>

Call `get_task` tool to check status:
- First query after 30 seconds
- Then every 30 seconds
- Extract image URL when status is `completed`

</details>

<details>
<summary><b>Script Method</b></summary>

**Single query:**
```bash
python .cursor/skills/seedance2-api/scripts/seedance_api.py query \
  --task-id "TASK_ID_HERE"
```

**Auto-poll (recommended for images, interval 10s, timeout 180s):**
```bash
python .cursor/skills/seedance2-api/scripts/seedance_api.py poll \
  --task-id "TASK_ID_HERE" --interval 10 --timeout 180
```

</details>

### image_size Reference

| Aspect Ratio | Recommended image_size | Note |
|--------------|------------------------|------|
| 16:9 | landscape_16_9 | Landscape |
| 9:16 | portrait_16_9 | Portrait |
| 4:3 | landscape_4_3 | Landscape |
| 3:4 | portrait_4_3 | Portrait |
| 1:1 | square_hd | Square |
| 21:9 | landscape_16_9 | Approximate ultrawide |

## Step 5: Compose the Final Prompt

Merge the storyboard structure and reference images into the final prompt:

- Use `@image_file_1`, `@image_file_2`, etc. to reference images in the image_files array
- Use `@video_file_1`, etc. to reference videos in the video_files array
- Use `@audio_file_1`, etc. to reference audio in the audio_files array

**Reference syntax example:**

```
@image_file_1 as character reference, follow @video_file_1 camera movement, with @audio_file_1 as background music
```

**Important:** The Nth URL in `image_files` maps to `@image_file_N`. `video_files` and `audio_files` are independently numbered.

## Step 6: Submit Video Task

**Handle asset URLs:**
- Seedream-generated images: URL already available, use directly
- User-provided web images: use directly
- User-provided local images: upload first to get URL (see upload methods below)

### Upload Local Images

<details>
<summary><b>MCP Method</b></summary>

Call `upload_image` tool: image_url or image_data

</details>

<details>
<summary><b>Script Method</b></summary>

```bash
# Upload from URL
python .cursor/skills/seedance2-api/scripts/seedance_api.py upload \
  --image-url "https://example.com/image.png"

# Upload local file
python .cursor/skills/seedance2-api/scripts/seedance_api.py upload \
  --image-path "/path/to/local/image.png"
```

</details>

### Submit Seedance 2.0 Task (Omni Reference Mode)

<details>
<summary><b>MCP Method</b></summary>

Call `submit_task` tool:
- model_id: `st-ai/super-seed2`
- parameters:
  - prompt: the full prompt from Step 5
  - functionMode: `omni_reference` (default, can be omitted)
  - image_files: reference image URL array (up to 9, order matches @image_file_1/2/3...)
  - video_files: reference video URL array (up to 3, total duration ≤ 15s)
  - audio_files: reference audio URL array (up to 3)
  - ratio: aspect ratio (`16:9` / `9:16` / `1:1` / `21:9` / `4:3` / `3:4`)
  - duration: integer length (`4`–`15`)
  - model: `seedance_2.0_fast` (default, faster) or `seedance_2.0` (standard quality)

</details>

<details>
<summary><b>Script Method</b></summary>

```bash
python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \
  --model "st-ai/super-seed2" \
  --params '{
    "prompt": "Cinematic realistic sci-fi style, 15 seconds, 16:9...",
    "functionMode": "omni_reference",
    "image_files": ["https://img1.png", "https://img2.png"],
    "ratio": "16:9",
    "duration": 15,
    "model": "seedance_2.0_fast"
  }'
```

</details>

### Submit Seedance 2.0 Task (First & Last Frames Mode)

<details>
<summary><b>MCP Method</b></summary>

Call `submit_task` tool:
- model_id: `st-ai/super-seed2`
- parameters:
  - prompt: video description prompt
  - functionMode: `first_last_frames`
  - filePaths: image URL array (0 = text-to-video, 1 = first frame, 2 = first & last frames)
  - ratio: aspect ratio
  - duration: integer length
  - model: `seedance_2.0_fast` or `seedance_2.0`

</details>

<details>
<summary><b>Script Method</b></summary>

```bash
python .cursor/skills/seedance2-api