Skill 详情
seedance-2-5-reference-to-video
在RunComfy上使用Seedance 2.5,从最多9张图像、视频片段和音频参考生成参考引导的1080p视频。
使用前先检查
自动化审核只检查相关性,不代表安全审查或推荐。使用前请阅读来源中的说明。
SKILL.md
这段内容是审核时保存的快照。外部来源才是完整且最新的版本。
--- name: seedance-2-5-reference-to-video allowed-tools: Bash(runcomfy *) displayName: "Seedance 2.5 Reference to Video" description: > Generate reference-guided 1080p video with ByteDance Seedance 2.5 Reference to Video on RunComfy via the `runcomfy` CLI. Feed up to 9 reference images, 1-3 reference video clips, and 3 reference audio files into one call and get a 4-30 second 1080p clip with native synchronized audio, identity and style locked to your references. Documents the full input schema (images / videos / audios / aspect_ratio / duration / generate_audio), the counted-seconds billing model ($0.53 per second of reference video duration plus output duration), the 480p draft-then-deliver workflow, and when to route to Seedance 2.5 text-to-video, image-to-video, or Seedance 2.0 Pro instead. Calls `runcomfy run bytedance/seedance-2.5/reference-to-video/1080p`. Triggers on "seedance 2.5", "seedance 2.5 reference to video", "reference to video", "reference-to-video", "seedance 1080p", "ByteDance Seedance 2.5", "consistent character video", "style-locked video", or any explicit ask to generate video from reference images and clips. homepage: https://www.runcomfy.com license: MIT --- # Seedance 2.5 Reference to Video Reference-guided 1080p video from ByteDance. Hand it the images that must stay stable, a short clip that carries the camera motion, and a prompt that directs the action — it returns a delivery-resolution 1080p clip with synchronized audio. [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-2-5-reference-to-video&utm_content=home) · [Seedance 2.5 Reference to Video 1080p](https://www.runcomfy.com/models/bytedance/seedance-2.5/reference-to-video/1080p?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-2-5-reference-to-video&utm_content=bytedance-seedance-2.5-reference-to-video-1080p) · [480p draft tier](https://www.runcomfy.com/models/bytedance/seedance-2.5/reference-to-video/480p?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-2-5-reference-to-video&utm_content=bytedance-seedance-2.5-reference-to-video-480p) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-2-5-reference-to-video&utm_content=cli-docs-introduction) ## Install this skill ```bash npx skills add genmedia-labs/skills --skill seedance-2-5-reference-to-video -g ``` ## When to pick this model (vs siblings) Seedance 2.5 Reference to Video's distinct property is **reference-conditioned generation at delivery resolution**: identity, product geometry, and art direction come from your reference stack rather than from prose, and the output lands at 1080p so you are not upscaling a draft. RunComfy positions it for *consistent character finals, product reference films, and style-locked brand clips*. | You want | Use | |---|---| | Same character / product across many shots, at final resolution | **Seedance 2.5 Reference to Video 1080p** | | Camera move and rhythm copied from an existing clip | **Seedance 2.5 Reference to Video 1080p** (`videos`) | | Brand style locked by a moodboard, not described in prose | **Seedance 2.5 Reference to Video 1080p** (`images`) | | Cheap iteration on which references actually work | [Seedance 2.5 Reference to Video 480p](https://www.runcomfy.com/models/bytedance/seedance-2.5/reference-to-video/480p?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-2-5-reference-to-video&utm_content=bytedance-seedance-2.5-reference-to-video-480p) | | No references at all — prompt only | [Seedance 2.5 Text to Video 1080p](https://www.runcomfy.com/models/bytedance/seedance-2.5/text-to-video/1080p?utm_source=skills.sh&utm_medium=skill&utm_campaign=seedance-2-5-reference-to-video&utm_content=bytedance-seedance-2.5-text-to-video-1080p) | | Animate exactly one still | [Seedance 2.5 Image to Video 1080p](https://www.runcomfy.com/models/bytedance/seedance-2.5/image-to-video/1在 GitHub 阅读完整来源 (打开外部页面)