[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77RWRPC1BRBPHD2NJVST70Z":3,"skill-same:01M77RWRPC1BRBPHD2NJVST70Z":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M77RWRPC1BRBPHD2NJVST70Z","doany-image-to-video",null,"Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run \u003Cvendor>\u002F\u003Cmodel>\u002Fimage-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on \"image to video\", \"image-to-video\", \"i2v\", \"animate image\", \"make this move\", or any explicit ask to turn a still into video.","janpereira-dev\u002FskillsCurate","janpereira-dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6440548?v=4","01M6KKKXBFFK7QF5Y2JFXN35FF","Jan Pereira","01M77ND31QCT5KM25E1SW71M8F",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdoany-image-to-video\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: doany-image-to-video\ndisplayName: \"Image-to-Video — Pro Pack on RunComfy\"\ndescription: >\n  Animate any still image on RunComfy — this skill is a smart router\n  that matches the user's intent to the right i2v model in the\n  RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio,\n  identity preservation) for general animations, Wan 2.7 with\n  `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for\n  multi-modal animation from image + reference video + reference\n  audio. Bundles each model's documented prompting patterns so the\n  caller gets sharper output without burning iterations on the wrong\n  model. Calls `runcomfy run \u003Cvendor>\u002F\u003Cmodel>\u002Fimage-to-video` (or\n  endpoint variant) through the local RunComfy CLI. Triggers on\n  \"image to video\", \"image-to-video\", \"i2v\", \"animate image\", \"make\n  this move\", or any explicit ask to turn a still into video.\nhomepage: https:\u002F\u002Fwww.runcomfy.com\nlicense: MIT\n---\n\n# Image-to-Video — Pro Pack on RunComfy\n\n[runcomfy.com](https:\u002F\u002Fwww.runcomfy.com\u002F?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [HappyHorse I2V](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fhappyhorse\u002Fhappyhorse-1-0\u002Fimage-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [Wan 2.7](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fwan-ai\u002Fwan-2-7\u002Ftext-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [Seedance 2.0 Pro](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fbytedance\u002Fseedance-v2\u002Fpro?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [GitHub](https:\u002F\u002Fgithub.com\u002Fagentspace-so\u002Fruncomfy-skills\u002Ftree\u002Fmain\u002Fimage-to-video)\n\n**Image-to-video, intent-routed.** This skill doesn't lock you to one model — it picks the right i2v model in the RunComfy catalog based on what the user actually wants: portrait animation, custom-voiceover lip-sync, or multi-modal composition.\n\n```bash\nnpx skills add agentspace-so\u002Fruncomfy-skills --skill image-to-video -g\n```\n\n## Pick the right model for the user's intent\n\n| User intent | Model | Why |\n|---|---|---|\n| Animate a portrait — keep identity stable | **HappyHorse 1.0 I2V** | #1 on Artificial Analysis Arena (Elo 1392); strong facial fidelity |\n| Product reveal \u002F 360 \u002F macro motion | **HappyHorse 1.0 I2V** | Geometry preservation + smooth camera moves |\n| Native synchronized ambient audio in one pass | **HappyHorse 1.0 I2V** | In-pass audio synthesis |\n| Animate **and** lip-sync to a **custom voiceover track** | **Wan 2.7 + `audio_url`** | Accepts your own MP3\u002FWAV (3–30s, ≤15MB) and drives lip-sync to it |\n| Multi-language dub variants (same image, different audio per call) | **Wan 2.7 + `audio_url`** | Same shot, swap `audio_url` per language |\n| Multi-modal — image + reference video + reference audio together | **Seedance 2.0 Pro** | Up to 9 image refs, 3 video refs (2–15s each), 3 audio refs |\n| Brand-consistent narrative with character ref + scene ref + voice ref | **Seedance 2.0 Pro** | Image holds identity, video holds scene, audio holds voice |\n| Default if unspecified | **HappyHorse 1.0 I2V** | Best all-round quality + native audio |\n\nThe agent reads this table, classifies the user's intent, and picks the matching subsection below.\n\n## Prerequisites\n\n1. **RunComfy CLI** — `npm i -g @runcomfy\u002Fcli`\n2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.\n3. **CI \u002F containers** — set `RUNCOMFY_TOKEN=\u003Ctoken>`.\n4. **A source image URL** — JPEG\u002FPNG\u002FWebP, min 300px, ≤10MB; aspect 1:2.5 to 2.5:1 (HappyHorse) — other models have similar specs.\n\n---\n\n## Route 1: HappyHorse 1.0 I2V — default for portrait \u002F product \u002F general animation\n\n**Model**: `happyhorse\u002Fhappyhorse-1-0\u002Fimage-to-video` · **Arena rank**: #1 (Elo 1392)\n\n### Schema\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `image_url` | string | yes | — | JPEG\u002FJPG\u002FPNG\u002FWEBP. Min 300px. Aspect 1:2.5–2.5:1. ≤10MB. |\n| `prompt` | string | yes | — | ≤5000 non-CJK or 2500 CJK chars. **Motion \u002F camera \u002F lighting** description. |\n| `resolution` | enum | no | `1080P` | `720P` or `1080P`. |\n| `duration` | int | no | 5 | 3–15 seconds. |\n| `seed` | int | no | 0 | Reuse for variant comparisons. |\n| `watermark` | bool | no | true | Provider watermark toggle. |\n\nOutput aspect = input aspect. No independent reframing.\n\n### Invoke\n\n```bash\nruncomfy run happyhorse\u002Fhappyhorse-1-0\u002Fimage-to-video \\\n  --input '{\n    \"image_url\": \"https:\u002F\u002F...\u002Fportrait.jpg\",\n    \"prompt\": \"Gentle camera drift around the subject'\\''s face, subtle breathing motion, identity-stable features, soft natural light.\"\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n### Prompting tips\n\n- **Lead with motion verbs**: \"drift\", \"dolly in\", \"orbit\", \"tilt up\", \"reveal\", \"blink\", \"breathe\". Front-load what's MOVING.\n- **Don't restate the image** — the model sees it. Focus tokens on what changes.\n- **Preservation goals explicit**: \"identity-stable features\", \"packaging unchanged\", \"background geometry stable\".\n- **Lighting evolution**: \"rim light intensifying\", \"shadows shortening as camera rises\".\n- **One beat per clip** — single primary motion (orbit OR dolly OR tilt OR character action).\n\n---\n\n## Route 2: Wan 2.7 + `audio_url` — when the user has a custom voiceover\n\n**Model**: `wan-ai\u002Fwan-2-7\u002Ftext-to-video` (NOT `\u002Fimage-to-video` — Wan 2.7's t2v endpoint accepts an `audio_url` that drives lip-sync)\n\n**Note on i2v with Wan 2.7**: Wan 2.7's primary i2v animation isn't on a dedicated endpoint here. For pure i2v (image animated by motion prompt only), prefer **HappyHorse i2v**. Use Wan 2.7 specifically when the user has a custom audio track they want lip-synced to a generated talking-head clip.\n\n### Schema (Wan 2.7 t2v with audio)\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `prompt` | string | yes | — | Up to ~5000 chars. Describe the talking-head shot: framing, lighting, motion. |\n| `audio_url` | string | yes (for lip-sync) | — | WAV\u002FMP3, 3–30s, ≤15MB. **Drives lip-sync.** |\n| `aspect_ratio` | enum | no | `16:9` | `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. |\n| `resolution` | enum | no | `1080p` | `720p` or `1080p`. |\n| `duration` | enum | no | `5` | 2–15 (whole seconds). Match your audio length. |\n| `negative_prompt` | string | no | — | Concrete issues to avoid (e.g. \"no subtitles, no flicker\"). |\n| `seed` | int | no | — | Reproducibility. |\n\n### Invoke\n\n```bash\nruncomfy run wan-ai\u002Fwan-2-7\u002Ftext-to-video \\\n  --input '{\n    \"prompt\": \"Medium close-up of a confident spokesperson in a softly-lit recording booth, leaning slightly toward the camera, locked tripod, shallow DOF, warm key light from camera-left.\",\n    \"audio_url\": \"https:\u002F\u002F...\u002Fvoiceover-en.mp3\",\n    \"duration\": 12,\n    \"aspect_ratio\": \"9:16\"\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n### Prompting tips\n\n- **Describe the talking-head shot** — framing, lighting, lens feel. The audio drives the lip-sync; the prompt builds the visual frame around it.\n- **Match `duration` to audio length** — clip will be silent past the audio if too long.\n- **Use `negative_prompt` for issues**: `\"no subtitles, no flicker, no distorted hands\"`.\n- **For multi-language dubs** — same prompt, swap `audio_url` per call. Lock seed for visual consistency across languages.\n\n---\n\n## Route 3: Seedance 2.0 Pro — multi-modal animation (image + ref video + ref audio)\n\n**Model**: `bytedance\u002Fseedance-v2\u002Fpro`\n\nUse when the user wants a single clip that combines: a **subject image** + **scene from a reference video** + **voice tone from a reference audio**.\n\n### Schema (Seedance 2.0 Pro, i2v-relevant fields)\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `prompt` | string | yes | — | CN ≤500 chars OR EN ≤1000 words. |\n| `image_url` | array | yes (for i2v) | `[]` | 0–9 images. **First is the primary subject.** |\n| `video_url` | array | no | `[]` | 0–3 reference clips (MP4\u002FMOV), 2–15s each. |\n| `audio_url` | array | no | `[]` | 0–3 reference audio (WAV\u002FMP3), 2–15s, \u003C 15MB each. |\n| `aspect_ratio` | enum | no | `adaptive` | `adaptive`, `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`. |\n| `duration` | int | no | 5 | 4–15 (whole seconds). |\n| `resolution` | enum | no | `720p` | `480p` or `720p`. |\n| `generate_audio` | bool | no | true | In-pass synchronized speech \u002F SFX \u002F music. |\n| `seed` | int | no | — | Reproducibility. |\n\n### Invoke\n\n```bash\nruncomfy run bytedance\u002Fseedance-v2\u002Fpro \\\n  --input '{\n    \"prompt\": \"Subject from image 1 walks through the café in video 1, voice tone matches audio 1. Medium close-up, slow push-in, warm light, gentle ambience.\",\n    \"image_url\": [\"https:\u002F\u002F...\u002Fsubject.jpg\"],\n    \"video_url\": [\"https:\u002F\u002F...\u002Fcafe-locked-shot.mp4\"],\n    \"audio_url\": [\"https:\u002F\u002F...\u002Fvoice-tone.mp3\"],\n    \"duration\": 8\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n### Prompting tips\n\n- **Image vs text division** — use `image_url` for what must stay stable (face, costume, brand); use `prompt` for what should evolve (action, mood, lighting).\n- **Number the refs** in the prompt: `\"subject from image 1, lighting from video 1, voice from audio 1\"`. Seedance routes cues correctly.\n- **Reference media specs** — videos \u002F audio must be 2–15s; audio \u003C 15MB.\n- **Don't mix radically different aesthetics** — if image 1 is a watercolor and video 1 is photoreal, output drifts.\n\n---\n\n## Limitations\n\n- **Each route inherits its model's limits.** HappyHorse: 15s cap, output aspect = input aspect. Wan 2.7: 15s cap, audio 3–30s\u002F15MB. Seedance: 720p ceiling on this template, 15s cap.\n- **No multi-route blending.** This skill picks one model per call. If the user wants HappyHorse animation + Wan-style lip-sync in the same clip, that's two calls + a stitch (out of scope here).\n- **Brand-specific overrides** — if the user named a specific model variant not listed (e.g. Wan 2.6, Seedance 1.5), route to the corresponding brand skill (`wan-2-7`, `seedance-v2`) instead of forcing it through here.\n\n## Exit codes\n\n| code | meaning |\n|---|---|\n| 0  | success |\n| 64 | bad CLI args |\n| 65 | bad input JSON \u002F schema mismatch |\n| 69 | upstream 5xx |\n| 75 | retryable: timeout \u002F 429 |\n| 77 | not signed in or token rejected |\n\nFull reference: [docs.runcomfy.com\u002Fcli\u002Ftroubleshooting](https:\u002F\u002Fdocs.runcomfy.com\u002Fcli\u002Ftroubleshooting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video).\n\n## How it works\n\nThe skill picks one of HappyHorse 1.0 I2V \u002F Wan 2.7 t2v+audio \u002F Seedance 2.0 Pro based on user intent and invokes `runcomfy run \u003Cmodel_id>` with the matching JSON body. The CLI POSTs to the Model API, polls the request, fetches the result, and downloads any `.runcomfy.net`\u002F`.runcomfy.com` URL into `--output-dir`. `Ctrl-C` cancels the remote request before exit.\n\n## Security & Privacy\n\n- **Token storage**: `runcomfy login` writes the API token to `~\u002F.config\u002Fruncomfy\u002Ftoken.json` with mode 0600 (owner-only read\u002Fwrite). Set `RUNCOMFY_TOKEN` env var to bypass the file entirely in CI \u002F containers.\n- **Input boundary**: the user prompt is passed as a JSON string to the CLI via `--input`. The CLI does NOT shell-expand the prompt; it transmits the JSON body directly to the Model API over HTTPS. No shell injection surface from prompt content.\n- **Third-party content**: image \u002F mask \u002F video URLs you pass are fetched by the RunComfy model server, not by the CLI on your machine. Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit \u002F video-edit model.\n- **Outbound endpoints**: only `model-api.runcomfy.net` (request submission) and `*.runcomfy.net` \u002F `*.runcomfy.com` (download whitelist for generated outputs). No telemetry, no callbacks.\n- **Generated-file size cap**: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.","# Image-to-Video — Pro Pack on RunComfy\n\n[runcomfy.com](https:\u002F\u002Fwww.runcomfy.com\u002F?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [HappyHorse I2V](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fhappyhorse\u002Fhappyhorse-1-0\u002Fimage-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [Wan 2.7](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fwan-ai\u002Fwan-2-7\u002Ftext-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [Seedance 2.0 Pro](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fbytedance\u002Fseedance-v2\u002Fpro?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video) · [GitHub](https:\u002F\u002Fgithub.com\u002Fagentspace-so\u002Fruncomfy-skills\u002Ftree\u002Fmain\u002Fimage-to-video)\n\n**Image-to-video, intent-routed.** This skill doesn't lock you to one model — it picks the right i2v model in the RunComfy catalog based on what the user actually wants: portrait animation, custom-voiceover lip-sync, or multi-modal composition.\n\n```bash\nnpx skills add agentspace-so\u002Fruncomfy-skills --skill image-to-video -g\n```\n\n## Pick the right model for the user's intent\n\n| User intent | Model | Why |\n|---|---|---|\n| Animate a portrait — keep identity stable | **HappyHorse 1.0 I2V** | #1 on Artificial Analysis Arena (Elo 1392); strong facial fidelity |\n| Product reveal \u002F 360 \u002F macro motion | **HappyHorse 1.0 I2V** | Geometry preservation + smooth camera moves |\n| Native synchronized ambient audio in one pass | **HappyHorse 1.0 I2V** | In-pass audio synthesis |\n| Animate **and** lip-sync to a **custom voiceover track** | **Wan 2.7 + `audio_url`** | Accepts your own MP3\u002FWAV (3–30s, ≤15MB) and drives lip-sync to it |\n| Multi-language dub variants (same image, different audio per call) | **Wan 2.7 + `audio_url`** | Same shot, swap `audio_url` per language |\n| Multi-modal — image + reference video + reference audio together | **Seedance 2.0 Pro** | Up to 9 image refs, 3 video refs (2–15s each), 3 audio refs |\n| Brand-consistent narrative with character ref + scene ref + voice ref | **Seedance 2.0 Pro** | Image holds identity, video holds scene, audio holds voice |\n| Default if unspecified | **HappyHorse 1.0 I2V** | Best all-round quality + native audio |\n\nThe agent reads this table, classifies the user's intent, and picks the matching subsection below.\n\n## Prerequisites\n\n1. **RunComfy CLI** — `npm i -g @runcomfy\u002Fcli`\n2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.\n3. **CI \u002F containers** — set `RUNCOMFY_TOKEN=\u003Ctoken>`.\n4. **A source image URL** — JPEG\u002FPNG\u002FWebP, min 300px, ≤10MB; aspect 1:2.5 to 2.5:1 (HappyHorse) — other models have similar specs.\n\n---\n\n## Route 1: HappyHorse 1.0 I2V — default for portrait \u002F product \u002F general animation\n\n**Model**: `happyhorse\u002Fhappyhorse-1-0\u002Fimage-to-video` · **Arena rank**: #1 (Elo 1392)\n\n### Schema\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `image_url` | string | yes | — | JPEG\u002FJPG\u002FPNG\u002FWEBP. Min 300px. Aspect 1:2.5–2.5:1. ≤10MB. |\n| `prompt` | string | yes | — | ≤5000 non-CJK or 2500 CJK chars. **Motion \u002F camera \u002F lighting** description. |\n| `resolution` | enum | no | `1080P` | `720P` or `1080P`. |\n| `duration` | int | no | 5 | 3–15 seconds. |\n| `seed` | int | no | 0 | Reuse for variant comparisons. |\n| `watermark` | bool | no | true | Provider watermark toggle. |\n\nOutput aspect = input aspect. No independent reframing.\n\n### Invoke\n\n```bash\nruncomfy run happyhorse\u002Fhappyhorse-1-0\u002Fimage-to-video \\\n  --input '{\n    \"image_url\": \"https:\u002F\u002F...\u002Fportrait.jpg\",\n    \"prompt\": \"Gentle camera drift around the subject'\\''s face, subtle breathing motion, identity-stable features, soft natural light.\"\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n### Prompting tips\n\n- **Lead with motion verbs**: \"drift\", \"dolly in\", \"orbit\", \"tilt up\", \"reveal\", \"blink\", \"breathe\". Front-load what's MOVING.\n- **Don't restate the image** — the model sees it. Focus tokens on what changes.\n- **Preservation goals explicit**: \"identity-stable features\", \"packaging unchanged\", \"background geometry stable\".\n- **Lighting evolution**: \"rim light intensifying\", \"shadows shortening as camera rises\".\n- **One beat per clip** — single primary motion (orbit OR dolly OR tilt OR character action).\n\n---\n\n## Route 2: Wan 2.7 + `audio_url` — when the user has a custom voiceover\n\n**Model**: `wan-ai\u002Fwan-2-7\u002Ftext-to-video` (NOT `\u002Fimage-to-video` — Wan 2.7's t2v endpoint accepts an `audio_url` that drives lip-sync)\n\n**Note on i2v with Wan 2.7**: Wan 2.7's primary i2v animation isn't on a dedicated endpoint here. For pure i2v (image animated by motion prompt only), prefer **HappyHorse i2v**. Use Wan 2.7 specifically when the user has a custom audio track they want lip-synced to a generated talking-head clip.\n\n### Schema (Wan 2.7 t2v with audio)\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `prompt` | string | yes | — | Up to ~5000 chars. Describe the talking-head shot: framing, lighting, motion. |\n| `audio_url` | string | yes (for lip-sync) | — | WAV\u002FMP3, 3–30s, ≤15MB. **Drives lip-sync.** |\n| `aspect_ratio` | enum | no | `16:9` | `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. |\n| `resolution` | enum | no | `1080p` | `720p` or `1080p`. |\n| `duration` | enum | no | `5` | 2–15 (whole seconds). Match your audio length. |\n| `negative_prompt` | string | no | — | Concrete issues to avoid (e.g. \"no subtitles, no flicker\"). |\n| `seed` | int | no | — | Reproducibility. |\n\n### Invoke\n\n```bash\nruncomfy run wan-ai\u002Fwan-2-7\u002Ftext-to-video \\\n  --input '{\n    \"prompt\": \"Medium close-up of a confident spokesperson in a softly-lit recording booth, leaning slightly toward the camera, locked tripod, shallow DOF, warm key light from camera-left.\",\n    \"audio_url\": \"https:\u002F\u002F...\u002Fvoiceover-en.mp3\",\n    \"duration\": 12,\n    \"aspect_ratio\": \"9:16\"\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n### Prompting tips\n\n- **Describe the talking-head shot** — framing, lighting, lens feel. The audio drives the lip-sync; the prompt builds the visual frame around it.\n- **Match `duration` to audio length** — clip will be silent past the audio if too long.\n- **Use `negative_prompt` for issues**: `\"no subtitles, no flicker, no distorted hands\"`.\n- **For multi-language dubs** — same prompt, swap `audio_url` per call. Lock seed for visual consistency across languages.\n\n---\n\n## Route 3: Seedance 2.0 Pro — multi-modal animation (image + ref video + ref audio)\n\n**Model**: `bytedance\u002Fseedance-v2\u002Fpro`\n\nUse when the user wants a single clip that combines: a **subject image** + **scene from a reference video** + **voice tone from a reference audio**.\n\n### Schema (Seedance 2.0 Pro, i2v-relevant fields)\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `prompt` | string | yes | — | CN ≤500 chars OR EN ≤1000 words. |\n| `image_url` | array | yes (for i2v) | `[]` | 0–9 images. **First is the primary subject.** |\n| `video_url` | array | no | `[]` | 0–3 reference clips (MP4\u002FMOV), 2–15s each. |\n| `audio_url` | array | no | `[]` | 0–3 reference audio (WAV\u002FMP3), 2–15s, \u003C 15MB each. |\n| `aspect_ratio` | enum | no | `adaptive` | `adaptive`, `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`. |\n| `duration` | int | no | 5 | 4–15 (whole seconds). |\n| `resolution` | enum | no | `720p` | `480p` or `720p`. |\n| `generate_audio` | bool | no | true | In-pass synchronized speech \u002F SFX \u002F music. |\n| `seed` | int | no | — | Reproducibility. |\n\n### Invoke\n\n```bash\nruncomfy run bytedance\u002Fseedance-v2\u002Fpro \\\n  --input '{\n    \"prompt\": \"Subject from image 1 walks through the café in video 1, voice tone matches audio 1. Medium close-up, slow push-in, warm light, gentle ambience.\",\n    \"image_url\": [\"https:\u002F\u002F...\u002Fsubject.jpg\"],\n    \"video_url\": [\"https:\u002F\u002F...\u002Fcafe-locked-shot.mp4\"],\n    \"audio_url\": [\"https:\u002F\u002F...\u002Fvoice-tone.mp3\"],\n    \"duration\": 8\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n### Prompting tips\n\n- **Image vs text division** — use `image_url` for what must stay stable (face, costume, brand); use `prompt` for what should evolve (action, mood, lighting).\n- **Number the refs** in the prompt: `\"subject from image 1, lighting from video 1, voice from audio 1\"`. Seedance routes cues correctly.\n- **Reference media specs** — videos \u002F audio must be 2–15s; audio \u003C 15MB.\n- **Don't mix radically different aesthetics** — if image 1 is a watercolor and video 1 is photoreal, output drifts.\n\n---\n\n## Limitations\n\n- **Each route inherits its model's limits.** HappyHorse: 15s cap, output aspect = input aspect. Wan 2.7: 15s cap, audio 3–30s\u002F15MB. Seedance: 720p ceiling on this template, 15s cap.\n- **No multi-route blending.** This skill picks one model per call. If the user wants HappyHorse animation + Wan-style lip-sync in the same clip, that's two calls + a stitch (out of scope here).\n- **Brand-specific overrides** — if the user named a specific model variant not listed (e.g. Wan 2.6, Seedance 1.5), route to the corresponding brand skill (`wan-2-7`, `seedance-v2`) instead of forcing it through here.\n\n## Exit codes\n\n| code | meaning |\n|---|---|\n| 0  | success |\n| 64 | bad CLI args |\n| 65 | bad input JSON \u002F schema mismatch |\n| 69 | upstream 5xx |\n| 75 | retryable: timeout \u002F 429 |\n| 77 | not signed in or token rejected |\n\nFull reference: [docs.runcomfy.com\u002Fcli\u002Ftroubleshooting](https:\u002F\u002Fdocs.runcomfy.com\u002Fcli\u002Ftroubleshooting?utm_source=skills.sh&utm_medium=skill&utm_campaign=image-to-video).\n\n## How it works\n\nThe skill picks one of HappyHorse 1.0 I2V \u002F Wan 2.7 t2v+audio \u002F Seedance 2.0 Pro based on user intent and invokes `runcomfy run \u003Cmodel_id>` with the matching JSON body. The CLI POSTs to the Model API, polls the request, fetches the result, and downloads any `.runcomfy.net`\u002F`.runcomfy.com` URL into `--output-dir`. `Ctrl-C` cancels the remote request before exit.\n\n## Security & Privacy\n\n- **Token storage**: `runcomfy login` writes the API token to `~\u002F.config\u002Fruncomfy\u002Ftoken.json` with mode 0600 (owner-only read\u002Fwrite). Set `RUNCOMFY_TOKEN` env var to bypass the file entirely in CI \u002F containers.\n- **Input boundary**: the user prompt is passed as a JSON string to the CLI via `--input`. The CLI does NOT shell-expand the prompt; it transmits the JSON body directly to the Model API over HTTPS. No shell injection surface from prompt content.\n- **Third-party content**: image \u002F mask \u002F video URLs you pass are fetched by the RunComfy model server, not by the CLI on your machine. Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit \u002F video-edit model.\n- **Outbound endpoints**: only `model-api.runcomfy.net` (request submission) and `*.runcomfy.net` \u002F `*.runcomfy.com` (download whitelist for generated outputs). No telemetry, no callbacks.\n- **Generated-file size cap**: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.",{"name":5,"license":15,"homepage":24,"description":25,"displayName":26},"https:\u002F\u002Fwww.runcomfy.com","Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run \u003Cvendor>\u002F\u003Cmodel>\u002Fimage-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on \"image to video\", \"image-to-video\", \"i2v\", \"animate image\", \"make this move\", or any explicit ask to turn a still into video.\n","Image-to-Video — Pro Pack on RunComfy","main","ba43a4e7e8b0fd6b150b14bcb48978ec40879a28",".agents\u002Fskills\u002Fdoany-image-to-video","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev","IT Leader, Scrum Master, FullStack Developer, SEO\u002FSEM Master #Angular #React\r\n","2026-07-13 03:04:32",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add janpereira-dev\u002FskillsCurate --skill doany-image-to-video",{"tool":40,"command":41},"bunx","bunx skills add janpereira-dev\u002FskillsCurate --skill doany-image-to-video",{"tool":43,"command":44},"pnpm","pnpm dlx skills add janpereira-dev\u002FskillsCurate --skill doany-image-to-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdoany-image-to-video\u002FSKILL.md",true,[],[49,57,64,71,78,86],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M77T9KN6TEJMPPTQZDEB4K61","zustand-5","Zustand 5 state management patterns. Trigger: When managing React state with Zustand.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzustand-5\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M77T9GN2GABPPWDGDCXJ6QWK","zod-4","Zod 4 schema validation patterns. Trigger: When using Zod for validation - breaking changes from v3.","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fzod-4\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M77T98A9R6PK155P71VX9MND","work-unit-commits","Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwork-unit-commits\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M77T9505TGQGWHGAYVXGE2KS","web-quality-audit","Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to \"audit my site\", \"review web quality\", \"run lighthouse audit\", \"check page quality\", or \"optimize my website\".","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-quality-audit\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":53,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M77T8YRVRNK8W4MG63XM80NK","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M77T8CEPQFZRRNGBYZX46P4Y","vercel-react-view-transitions","Guide for implementing smooth, native-feeling animations using React's View Transition API (`\u003CViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter\u002Fexit of components, animate list reorder, implement directional (forward\u002Fback) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.","https:\u002F\u002Fgithub.com\u002Fjanpereira-dev\u002FskillsCurate\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvercel-react-view-transitions\u002FSKILL.md",[],[]]