Ai Image To Video Keyframe

Skip the learning curve of professional editing software. Describe what you want — animate these images as keyframes into a smooth video sequence — and get a...

Security Scan

The skill's networking and token usage align with its stated image-to-video purpose, but there are inconsistencies and unnecessary filesystem probes (install-path/config-path detection) that warrant caution before installing.

Purpose & Capability

Name/description match the runtime actions (upload images, create render jobs on nemovideo.ai) and the single required credential (NEMO_TOKEN) is consistent with a cloud service API. However, the skill's frontmatter references a config path (~/.config/nemovideo/) and runtime instructions ask the agent to detect install paths (~/.clawhub/, ~/.cursor/skills/), while the registry metadata earlier listed no required config paths — this mismatch is an inconsistency to clarify.

Instruction Scope

SKILL.md instructs the agent to: read this file's YAML frontmatter at runtime, detect platform by inspecting specific filesystem paths in the user's home (e.g., ~/.clawhub/, ~/.cursor/skills/), upload local files via multipart, obtain or reuse NEMO_TOKEN, and persist session_id. Reading other install directories and home config paths is outside the minimal need to call the API and is privacy-sensitive. All API calls are targeted to mega-api-prod.nemovideo.ai (no unrelated endpoints).

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by an install process. This is the lowest-risk install model.

Credentials

Only one credential is required (NEMO_TOKEN), which matches the API's Bearer auth usage. However, the SKILL.md frontmatter refers to a config path (~/.config/nemovideo/) while the skill manifest listed none; that mismatch suggests either the metadata is stale or the skill expects additional local config access not declared up-front.

Persistence & Privilege

Skill does not request always:true and is user-invocable. It instructs storing session_id for operation continuity, which is reasonable for long-running render jobs. It does not ask to modify other skills or global settings.

What to consider before installing

This skill otherwise behaves like a normal cloud image-to-video integration, but before installing you should: 1) Confirm what NEMO_TOKEN is (who issues it and what scopes/retention it has). 2) Ask the skill author to explain why the agent must inspect ~/.* install paths and a ~/.config/nemovideo/ config path — this exposes parts of your home directory unnecessarily; prefer returning 'unknown' or using agent-provided platform metadata instead. 3) Verify the endpoints (mega-api-prod.nemovideo.ai) are official and acceptable to you. 4) Be cautious about uploading sensitive images to any third-party service and prefer using an ephemeral anonymous token (the skill supports creating one) if you don't want to use a long-lived token. If the developer clarifies the config-path/metadata mismatch and removes filesystem scanning, the risk would be much lower.

Getting Started

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

Try saying:

• "convert my images"
• "export 1080p MP4"
• "animate these images as keyframes into"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

AI Image to Video Keyframe — Convert Images into Keyframe Videos

This tool takes your images and runs AI keyframe video generation through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have two product shots or scene illustrations and want to animate these images as keyframes into a smooth video sequence — the backend processes it in about 30-90 seconds and hands you a 1080p MP4.

Tip: use images with similar compositions for smoother keyframe interpolation.

Matching Input to Actions

User prompts referencing ai image to video keyframe, 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.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: ai-image-to-video-keyframe
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else 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.

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

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)

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Common Workflows

Quick edit: Upload → "animate these images as keyframes into a smooth video sequence" → 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 "animate these images as keyframes into a smooth video sequence" — concrete instructions get better results.

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

PNG images preserve the most detail for cleaner keyframe rendering.