{"skill":{"slug":"image-to-video-end-frame","displayName":"Image To Video End Frame","summary":"generate images into image-ending video with this skill. Works with JPG, PNG, WEBP, HEIC files up to 200MB. marketers, social media creators, animators use i...","description":"---\nname: image-to-video-end-frame\nversion: \"1.0.0\"\ndisplayName: \"Image to Video End Frame β€” Generate Videos With Controlled End Frame\"\ndescription: >\n generate images into image-ending video with this skill. Works with JPG, PNG, WEBP, HEIC files up to 200MB. marketers, social media creators, animators use it for creating videos that animate toward a specific ending image β€” processing takes 30-60 seconds on cloud GPUs and you get 1080p MP4 files.\nmetadata: {\"openclaw\": {\"emoji\": \"πŸ–ΌοΈ\", \"requires\": {\"env\": [\"NEMO_TOKEN\"], \"configPaths\": [\"~/.config/nemovideo/\"]}, \"primaryEnv\": \"NEMO_TOKEN\", \"variant\": \"short_prompts\"}}\n---\n\n## Getting Started\n\n> Share your images and I'll get started on AI video generation. Or just tell me what you're thinking.\n\n**Try saying:**\n- \"generate my images\"\n- \"export 1080p MP4\"\n- \"generate a video that ends on\"\n\n### Getting Connected\n\nBefore handling any user request, establish a connection to the backend API. Show a brief status like \"Connecting...\".\n\n**If `NEMO_TOKEN` is in the environment**, use it directly and create a session. Otherwise, acquire a free starter token:\n- Generate a UUID as client identifier\n- POST to `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token` with the `X-Client-Id` header\n- The response includes a `token` with 100 free credits valid for 7 days β€” use it as NEMO_TOKEN\n\n**Then create a session** by POSTing to `https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent` with Bearer authorization and body `{\"task_name\":\"project\",\"language\":\"en\"}`. The `session_id` in the response is needed for all following requests.\n\nTell the user you're ready. Keep the technical details out of the chat.\n\n# Image to Video End Frame β€” Generate Videos With Controlled End Frame\n\nSend me your images and describe the result you want. The AI video generation runs on remote GPU nodes β€” nothing to install on your machine.\n\nA quick example: upload a product photo used as the final frame of a video, type \"generate a video that ends on this image as the last frame\", and you'll get a 1080p MP4 back in roughly 30-60 seconds. All rendering happens server-side.\n\nWorth noting: high-contrast images with clear subjects work best as end frames for smooth transitions.\n\n## Matching Input to Actions\n\nUser prompts referencing image to video end frame, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.\n\n| User says... | Action | Skip SSE? |\n|-------------|--------|----------|\n| \"export\" / \"ε―Όε‡Ί\" / \"download\" / \"send me the video\" | β†’ Β§3.5 Export | βœ… |\n| \"credits\" / \"η§―εˆ†\" / \"balance\" / \"余钝\" | β†’ Β§3.3 Credits | βœ… |\n| \"status\" / \"ηŠΆζ€\" / \"show tracks\" | β†’ Β§3.4 State | βœ… |\n| \"upload\" / \"上传\" / user sends file | β†’ Β§3.2 Upload | βœ… |\n| Everything else (generate, edit, add BGM…) | β†’ Β§3.1 SSE | ❌ |\n\n## Cloud Render Pipeline Details\n\nEach export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.\n\n**All requests** must include: `Authorization: Bearer `, `X-Skill-Source`, `X-Skill-Version`, `X-Skill-Platform`. Missing attribution headers will cause export to fail with 402.\n\nSkill attribution β€” read from this file's YAML frontmatter at runtime:\n- `X-Skill-Source`: `image-to-video-end-frame`\n- `X-Skill-Version`: from frontmatter `version`\n- `X-Skill-Platform`: detect from install path (`~/.clawhub/` β†’ `clawhub`, `~/.cursor/skills/` β†’ `cursor`, else `unknown`)\n\n**API base**: `https://mega-api-prod.nemovideo.ai`\n\n**Create session**: POST `/api/tasks/me/with-session/nemo_agent` β€” body `{\"task_name\":\"project\",\"language\":\"\"}` β€” returns `task_id`, `session_id`.\n\n**Send message (SSE)**: POST `/run_sse` β€” body `{\"app_name\":\"nemo_agent\",\"user_id\":\"me\",\"session_id\":\"\",\"new_message\":{\"parts\":[{\"text\":\"\"}]}}` with `Accept: text/event-stream`. Max timeout: 15 minutes.\n\n**Upload**: POST `/api/upload-video/nemo_agent/me/` β€” file: multipart `-F \"files=@/path\"`, or URL: `{\"urls\":[\"\"],\"source_type\":\"url\"}`\n\n**Credits**: GET `/api/credits/balance/simple` β€” returns `available`, `frozen`, `total`\n\n**Session state**: GET `/api/state/nemo_agent/me//latest` β€” key fields: `data.state.draft`, `data.state.video_infos`, `data.state.generated_media`\n\n**Export** (free, no credits): POST `/api/render/proxy/lambda` β€” body `{\"id\":\"render_\",\"sessionId\":\"\",\"draft\":,\"output\":{\"format\":\"mp4\",\"quality\":\"high\"}}`. Poll GET `/api/render/proxy/lambda/` every 30s until `status` = `completed`. Download URL at `output.url`.\n\nSupported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.\n\n### Error Handling\n\n| Code | Meaning | Action |\n|------|---------|--------|\n| 0 | Success | Continue |\n| 1001 | Bad/expired token | Re-auth via anonymous-token (tokens expire after 7 days) |\n| 1002 | Session not found | New session Β§3.0 |\n| 2001 | No credits | Anonymous: show registration URL with `?bind=` (get `` from create-session or state response when needed). Registered: \"Top up credits in your account\" |\n| 4001 | Unsupported file | Show supported formats |\n| 4002 | File too large | Suggest compress/trim |\n| 400 | Missing X-Client-Id | Generate Client-Id and retry (see Β§1) |\n| 402 | Free plan export blocked | Subscription tier issue, NOT credits. \"Register or upgrade your plan to unlock export.\" |\n| 429 | Rate limit (1 token/client/7 days) | Retry in 30s once |\n\n### Backend Response Translation\n\nThe backend assumes a GUI exists. Translate these into API actions:\n\n| Backend says | You do |\n|-------------|--------|\n| \"click [button]\" / \"点击\" | Execute via API |\n| \"open [panel]\" / \"打开\" | Query session state |\n| \"drag/drop\" / \"ζ‹–ζ‹½\" | Send edit via SSE |\n| \"preview in timeline\" | Show track summary |\n| \"Export button\" / \"ε―Όε‡Ί\" | Execute export workflow |\n\n### SSE Event Handling\n\n| Event | Action |\n|-------|--------|\n| Text response | Apply GUI translation (Β§4), present to user |\n| Tool call/result | Process internally, don't forward |\n| `heartbeat` / empty `data:` | Keep waiting. Every 2 min: \"⏳ Still working...\" |\n| Stream closes | Process final response |\n\n~30% of editing operations return no text in the SSE stream. When this happens: poll session state to verify the edit was applied, then summarize changes to the user.\n\nDraft JSON uses short keys: `t` for tracks, `tt` for track type (0=video, 1=audio, 7=text), `sg` for segments, `d` for duration in ms, `m` for metadata.\n\nExample timeline summary:\n```\nTimeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: \"Urban Dreams\" (0-3s)\n```\n\n## Common Workflows\n\n**Quick edit**: Upload β†’ \"generate a video that ends on this image as the last frame\" β†’ Download MP4. Takes 30-60 seconds for a 30-second clip.\n\n**Batch style**: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.\n\n**Iterative**: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.\n\n## Tips and Tricks\n\nThe backend processes faster when you're specific. Instead of \"make it look better\", try \"generate a video that ends on this image as the last frame\" β€” concrete instructions get better results.\n\nMax file size is 200MB. Stick to JPG, PNG, WEBP, HEIC for the smoothest experience.\n\nExport as MP4 for widest compatibility.\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":311,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1777868031306,"updatedAt":1778492842520},"latestVersion":{"version":"1.0.0","createdAt":1777868031306,"changelog":"Initial release β€” generate videos from images with a controlled end frame.\n\n- Supports JPG, PNG, WEBP, HEIC uploads up to 200MB for video creation.\n- Session-based GPU video rendering; receive 1080p MP4 output in 30–90 seconds.\n- Automatic handling of authentication and session setup, including free credit tokens.\n- Workflow includes image upload, AI-powered animation toward an ending image, and easy export.\n- Built-in error handling for authentication, file limits, format issues, and export permissions.\n- Summarizes timeline edits and guides users with clear status messages throughout the process.","license":"MIT-0"},"metadata":{"setup":[{"key":"NEMO_TOKEN","required":true}],"os":null,"systems":null},"owner":{"handle":"mory128","userId":"s178x6tah7eg67gtzqsb5g5gwd84dd48","displayName":"mory128","image":"https://avatars.githubusercontent.com/u/270709915?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1780090738880}}