Image To Video Local Ai

convert still images into animated video clips with this skill. Works with JPG, PNG, WEBP, BMP files up to 200MB. creators and developers use it for converti...

Security Scan

The skill claims to be a "Local AI" image→video tool but its runtime instructions upload images and create session tokens on a cloud backend (mega-api-prod.nemovideo.ai); that mismatch and a few metadata inconsistencies make the package suspicious.

Purpose & Capability

The skill name and description emphasize "Local AI" processing, but the SKILL.md repeatedly documents a cloud backend (mega-api-prod.nemovideo.ai), session creation, file uploads, and cloud GPU rendering. Requiring NEMO_TOKEN and instructing uploads to the remote API are coherent with a cloud service but contradict the "local" claim; this is misleading and could cause unexpected data exfiltration.

Instruction Scope

The instructions direct the agent to check for NEMO_TOKEN, and if missing automatically POST to an anonymous-token endpoint to obtain one, create sessions, upload files (multipart or URL), run SSE endpoints, poll render jobs, and return download URLs. Those steps are within the stated cloud-rendering workflow, but they explicitly cause user images to be uploaded to an external service and create bearer tokens automatically. The skill also expects to derive headers from install paths (detecting ~/.clawhub/ or ~/.cursor/skills/), implying the agent may inspect filesystem/installation context. The behavior is not out-of-scope for a cloud rendering skill, but it contradicts the advertised "local" processing and includes automatic token issuance and uploads that users should be warned about.

Install Mechanism

This is instruction-only with no install spec and no code files, so nothing is written to disk by an installer. That lowers surface risk from installation artifacts.

Credentials

Only one required environment variable (NEMO_TOKEN) is declared, which matches the cloud API authentication model. However, the SKILL.md metadata also references a config path (~/.config/nemovideo/) which is not listed in the registry summary — this inconsistency is noteworthy. The skill will create an anonymous token itself if NEMO_TOKEN is absent, which is functional but expands the skill's network activity and credential lifecycle (temporary anonymous tokens, 7-day expiry).

Persistence & Privilege

The skill is not always-enabled and does not request system-wide privileges in its metadata. It instructs keeping session_id for operations (normal for API sessions) but does not request persistent modification of other skills or system settings.

What to consider before installing

This skill is labelled "Local AI" but actually sends images to mega-api-prod.nemovideo.ai and creates/uses bearer tokens — so it will upload your images and metadata to a third party. Before installing or using it, consider: - Treat it as a cloud service, not an on-device/local model. Do not upload sensitive or private images unless you trust the remote service and its privacy policy. - The skill will automatically obtain anonymous tokens if NEMO_TOKEN isn't set; that means it can initiate outbound network calls without explicit manual token configuration. - There is a metadata mismatch (registry said no config paths but SKILL.md references ~/.config/nemovideo/ and install-path detection). Ask the publisher where session tokens and any cached files are stored and whether anything is persisted to disk. - No source or homepage is provided. Prefer skills with a known homepage or repository so you can inspect privacy practices and API owners. - If you decide to try it, monitor network traffic or use a disposable account/token, and avoid sending sensitive imagery until you verify the provider and retention policy. If you want, I can draft questions to ask the skill author (data retention, where tokens are stored, whether uploads are retained, proof the processing is local vs cloud) or help you choose an alternative that truly runs models locally.

Getting Started

Share your still images and I'll get started on local AI video creation. Or just tell me what you're thinking.

Try saying:

• "convert my still images"
• "export 1080p MP4"
• "turn these images into a smooth"

Quick Start Setup

This skill connects to a cloud processing backend. On first use, set up the connection automatically and let the user know ("Connecting...").

Token check: Look for NEMO_TOKEN in the environment. If found, skip to session creation. Otherwise:

• Generate a UUID as client identifier
• POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with X-Client-Id header
• Extract data.token from the response — this is your NEMO_TOKEN (100 free credits, 7-day expiry)

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Image to Video Local AI — Convert Images into Video Clips

Drop your still images in the chat and tell me what you need. I'll handle the local AI video creation on cloud GPUs — you don't need anything installed locally.

Here's a typical use: you send a three product photos in JPG format, ask for turn these images into a smooth video with transitions and motion effects, and about 1-3 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — fewer images with higher resolution tend to produce smoother motion output.

Matching Input to Actions

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

User says...	Action	Skip 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.

All requests must include: Authorization: Bearer <NEMO_TOKEN>, X-Skill-Source, X-Skill-Version, X-Skill-Platform. Missing attribution headers will cause export to fail with 402.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is image-to-video-local-ai, X-Skill-Version comes from the version field, and X-Skill-Platform is detected from the install path (~/.clawhub/ = clawhub, ~/.cursor/skills/ = cursor, otherwise unknown).

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Error Handling

Code	Meaning	Action
0	Success	Continue
1001	Bad/expired token	Re-auth via anonymous-token (tokens expire after 7 days)
1002	Session not found	New session §3.0
2001	No credits	Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up credits in your account"
4001	Unsupported file	Show supported formats
4002	File too large	Suggest compress/trim
400	Missing X-Client-Id	Generate Client-Id and retry (see §1)
402	Free plan export blocked	Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
429	Rate limit (1 token/client/7 days)	Retry in 30s once

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

SSE Event Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result	Process internally, don't forward
heartbeat / empty data:	Keep waiting. Every 2 min: "⏳ Still working..."
Stream closes	Process 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.

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 "turn these images into a smooth video with transitions and motion effects" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across devices and platforms.

Common Workflows

Quick edit: Upload → "turn these images into a smooth video with transitions and motion effects" → Download MP4. Takes 1-3 minutes 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.