image-to-video-finder

Get matched video results ready to post, without touching a single slider. Upload your images (JPG, PNG, WEBP, BMP, up to 200MB), say something like "find the video this image is from", and download 1080p MP4 when it's done. Built for researchers, content creators, marketers who move fast and want to locate the original video behind a still frame or screenshot.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "image-to-video-finder" with this command: npx skills add whitejohnk-26/image-to-video-finder

Getting Started

Share your images and I'll get started on video search and matching. Or just tell me what you're thinking.

Try saying:

  • "find my images"
  • "export 1080p MP4"
  • "find the video this image is"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

  1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
  2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Image to Video Finder — Find Videos From Images

Send me your images and describe the result you want. The video search and matching runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a screenshot from a movie scene, type "find the video this image is from", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: cropped or watermarked images may reduce match accuracy — use the clearest frame possible.

Matching Input to Actions

User prompts referencing image to video finder, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

User says...ActionSkip SSE?
"export" / "导出" / "download" / "send me the video"→ §3.5 Export
"credits" / "积分" / "balance" / "余额"→ §3.3 Credits
"status" / "状态" / "show tracks"→ §3.4 State
"upload" / "上传" / user sends file→ §3.2 Upload
Everything else (generate, edit, add BGM…)→ §3.1 SSE

Cloud Render Pipeline Details

Each 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.

Base URL: https://mega-api-prod.nemovideo.ai

EndpointMethodPurpose
/api/tasks/me/with-session/nemo_agentPOSTStart a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_ssePOSTSend a user message. Body includes app_name, session_id, new_message. Stream response with Accept: text/event-stream. Timeout: 15 min.
/api/upload-video/nemo_agent/me/<sid>POSTUpload a file (multipart) or URL.
/api/credits/balance/simpleGETCheck remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latestGETFetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambdaPOSTStart export. Body: {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll status every 30s.

Accepted file types: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Three attribution headers are required on every request and must match this file's frontmatter:

HeaderValue
X-Skill-Sourceimage-to-video-finder
X-Skill-Versionfrontmatter version
X-Skill-Platformauto-detect: clawhub / cursor / unknown from install path

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

Error Handling

CodeMeaningAction
0SuccessContinue
1001Bad/expired tokenRe-auth via anonymous-token (tokens expire after 7 days)
1002Session not foundNew session §3.0
2001No creditsAnonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001Unsupported fileShow supported formats
4002File too largeSuggest compress/trim
400Missing X-Client-IdGenerate Client-Id and retry (see §1)
402Free plan export blockedSubscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429Rate limit (1 token/client/7 days)Retry in 30s once

SSE Event Handling

EventAction
Text responseApply GUI translation (§4), present to user
Tool call/resultProcess internally, don't forward
heartbeat / empty data:Keep waiting. Every 2 min: "⏳ Still working..."
Stream closesProcess final response

~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.

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

  • "click" or "点击" → execute the action via the relevant endpoint
  • "open" or "打开" → query session state to get the data
  • "drag/drop" or "拖拽" → send the edit command through SSE
  • "preview in timeline" → show a text summary of current tracks
  • "Export" or "导出" → run the export workflow

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "find the video this image is from" — concrete instructions get better results.

Max file size is 200MB. Stick to JPG, PNG, WEBP, BMP for the smoothest experience.

PNG images retain more detail than JPG and tend to produce more accurate matches.

Common Workflows

Quick edit: Upload → "find the video this image is from" → Download MP4. Takes 20-40 seconds for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

通义晓蜜 - 智能外呼

触发阿里云晓蜜外呼机器人任务,自动批量拨打电话。适用于批量外呼、客户回访、满意度调查、简历筛查约面试等场景。可从前置工具或节点获取外呼名单。

Registry SourceRecently Updated
General

Letterboxd Watchlist

Scrape a public Letterboxd user's watchlist into a CSV/JSONL list of titles and film URLs without logging in. Use when a user asks to export, scrape, or mirror a Letterboxd watchlist, or to build watch-next queues.

Registry SourceRecently Updated
General

Seedance Video Generation

Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.

Registry SourceRecently Updated
4.2K17jackycser
General

Universal Skills Manager

The master coordinator for AI skills. Discovers skills from multiple sources (SkillsMP.com, SkillHub, and ClawHub), manages installation, and synchronization...

Registry SourceRecently Updated