Image To Video Model Ai

Skip the learning curve of professional editing software. Describe what you want — turn this image into a 5-second animated video clip with smooth motion — a...

Security Scan

The skill's behavior generally matches an image→video cloud service, but there are inconsistencies and privacy/secret-handling choices (automatic anonymous token creation and silent storage, a declared config path mismatch) that warrant caution before installing.

Purpose & Capability

Name/description match the instructions: the SKILL.md directs image upload, SSE-based editing, and cloud render/export calls to a nemovideo API. However, the skill's YAML frontmatter declares a config path (~/.config/nemovideo/) that is not reflected in the registry metadata provided earlier, and the skill also instructs the agent to inspect the install path to derive X-Skill-Platform. Those filesystem-access requirements are plausible for telemetry/attribution but are not justified in the public registry fields — this mismatch is unexpected.

Instruction Scope

Runtime instructions tell the agent to automatically call an anonymous-token endpoint when NEMO_TOKEN is not present, store the returned token/session_id, and 'don't display' raw tokens. They also instruct sending user files (up to 200MB) to a third-party API. These actions are coherent with a cloud render service, but the automatic creation/storage of credentials and the silent handling of tokens broaden the agent's behavior beyond simple request/response and create potential for persistent secrets and covert exfiltration of user images. The SKILL.md does not specify exactly where or how tokens/session IDs should be stored (file, memory, key store), which is a scope/opacity concern.

Install Mechanism

No install spec or code files are present (instruction-only). That is the lowest-risk install mechanism — nothing is being downloaded or written by an install step according to the metadata.

Credentials

Only one required env var (NEMO_TOKEN) is declared and is appropriate for a remote API. However, SKILL.md implements an automatic fallback that fetches a token if NEMO_TOKEN is absent and asks to persist the session token. The frontmatter also lists a config path (~/.config/nemovideo/) which the registry listing earlier did not; that is an inconsistency and implies the skill may read/write user config files beyond the declared env var.

Persistence & Privilege

always is false and the skill can be invoked autonomously (platform default). The skill does instruct storing session tokens, but it does not request elevated system privileges or to modify other skills/configs. Still, automatic token persistence increases long-term presence on the agent unless the user controls it.

What to consider before installing

This skill appears to implement a cloud-based image→video workflow and most requirements line up with that purpose, but take these precautions before installing or using it: - Privacy: Using the skill will upload your images to a third-party server. Do not send sensitive or private images unless you trust the service and its data retention policy. - Token handling: The skill will auto-request and store an anonymous token if you don't set NEMO_TOKEN yourself. If you prefer control, create and set NEMO_TOKEN manually rather than allowing automatic provisioning. Ask where tokens/session IDs are stored (file path or secure store) and how long they persist. - Config path mismatch: The SKILL.md mentions ~/.config/nemovideo/ and deriving X-Skill-Platform from install paths — the registry metadata did not list config paths. Ask the skill author to clarify what filesystem paths it reads/writes and to align registry metadata with SKILL.md. - Attribution headers: The skill requires custom headers derived from local paths. Confirm that determining X-Skill-Platform only requires checking the skill's own install location and does not cause wider filesystem scans. - Source trust: The skill has unknown source/homepage information. If you need higher assurance, request an author/contact or open-source code so you can inspect where tokens and user uploads are sent and persisted. If any of the above remain unclear or you cannot trust the remote domain, do not install or use this skill with sensitive data.

Getting Started

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

Try saying:

• "convert my still images"
• "export 1080p MP4"
• "turn this image into a 5-second"

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 Model AI — Convert Images into Video Clips

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

A quick example: upload a single product photo or landscape image, type "turn this image into a 5-second animated video clip with smooth motion", and you'll get a 1080p MP4 back in roughly 30-90 seconds. All rendering happens server-side.

Worth noting: high-contrast images with clear subjects produce the most natural-looking motion.

Matching Input to Actions

User prompts referencing image to video model 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.

Headers are derived from this file's YAML frontmatter. X-Skill-Source is image-to-video-model-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).

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.

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.

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.

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 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.

Example timeline summary:

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

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

Common Workflows

Quick edit: Upload → "turn this image into a 5-second animated video clip with smooth motion" → Download MP4. Takes 30-90 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "turn this image into a 5-second animated video clip with smooth motion" — concrete instructions get better results.

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

Export as MP4 for widest compatibility across social platforms and editors.