用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/SamurAIGPT/Seedance-2.5-API --skill seedance-v2命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | seedance-v2 |
| description | Generate cinematic, high-fidelity AI videos with the Seedance 2.5 API (by ByteDance) through MuAPI. |
| version | 1.1.0 |
| metadata | {"openclaw":{"requires":{"env":"[Truncated]","bins":"[Truncated]"},"emoji":"🎥","homepage":"https://muapi.ai","os":["macos","linux"]}} |
Seedance 2.5 is ByteDance's high-fidelity video generation model. This skill supports text-to-video, image animation, keyframe transitions, multimodal references, video editing, video extension, and character workflows.
You can select standard, Intl, or Spicy route variants and 480p, 720p, upscaled 1080p, or upscaled 4K tiers. Durations range from 4 to 30 seconds.
Generate a video from a descriptive text prompt.
python3.11 skills/seedance-v2/seedance_cli.py t2v --prompt "A cinematic slow-motion shot of a cyberpunk city in the rain" --variant intl --resolution 1080p --wait
Animate one static image.
python3.11 skills/seedance-v2/seedance_cli.py i2v --image_url "https://example.com/image.jpg" --prompt "Make the clouds move slowly" --wait
Generate a transition between exactly two images.
python3.11 skills/seedance-v2/seedance_cli.py first-last --images "https://example.com/start.jpg" "https://example.com/end.jpg" --prompt "Smoothly transition from day to night" --wait
Edit an existing video or apply styles.
python3.11 skills/seedance-v2/seedance_cli.py edit --video "https://example.com/video.mp4" --prompt "Turn the sunny afternoon into a rainy blue-hour scene" --wait
Condition videos on any combination of images, videos, and audio.
python3.11 skills/seedance-v2/seedance_cli.py omni --prompt "The character @character:ID dances in the rain" --images "https://example.com/bg.jpg" --videos "https://example.com/motion.mp4" --wait
Create a reusable character sheet for consistent generation.
python3.11 skills/seedance-v2/seedance_cli.py character --images "https://example.com/face.jpg" --outfit "Cyberpunk neon jacket" --name "Neo" --wait
Remove MuAPI watermarks from generated videos.
python3.11 skills/seedance-v2/seedance_cli.py watermark-remover --video_url "https://api.muapi.ai/..." --wait
Continue an existing video from its final frame.
python3.11 skills/seedance-v2/seedance_cli.py extend --video "https://example.com/video.mp4" --prompt "Continue the camera move into the city" --wait
Use the generate command when you need an exact route slug, including any
Intl or Spicy resolution variant.
python3.11 skills/seedance-v2/seedance_cli.py generate --endpoint seedance-2.5-spicy-video-edit-4k --video "https://example.com/video.mp4" --prompt "Change the lighting to a neon night scene" --wait
--wait flag to receive the final video URL directly. Without it, you will receive a request_id which you can check later using the status command.16:9 for horizontal videos and 9:16 for vertical content (like TikTok or Reels).--resolution; 1080p and 4K are upscaled from the 720p base render.--variant intl for the international route or --variant spicy for the relaxed-content-safety route.| Command | Arguments | Description |
|---|---|---|
t2v | --prompt, --variant, --resolution, --aspect_ratio, --duration, --seed, --wait | Text to Video |
i2v | --image_url, --prompt, --variant, --resolution, --aspect_ratio, --duration, --seed, --wait | Image to Video |
first-last | --images (exactly 2), --prompt, --variant, --resolution, --aspect_ratio, --duration, --seed, --wait | First & Last Frame |
omni | --prompt, --images, --videos, --audios, --variant, --resolution, --aspect_ratio, --duration, --seed, --wait | Omni Reference |
character | --images, --outfit, --name, --wait | Create Character Sheet |
edit | --prompt, --video, --variant, --resolution, --reference-images, --reference-audios, , |
--no-audio--wait| Video Edit |
watermark-remover | --video_url, --wait | Remove Watermark |
extend | --prompt, --video, --last-image, --variant, --resolution, --no-audio, --wait | Video Extend |
generate | --endpoint, --prompt, workflow-specific input flags, --wait | Any current Seedance 2.5 route |
status | --request_id | Check Task Status |