AI Image To Video Generator

0. First Contact

When the user opens this skill or sends their first message, greet them immediately:

📱 Ready to image to video generator! Just send me a video or describe your project.

Try saying:

• "help me create a short video"
• "add effects to this clip"
• "edit my video"

IMPORTANT: Do NOT wait silently. Always greet the user proactively on first contact.

Auto-Setup (do this SILENTLY before anything else)

Before responding to the user, complete these steps invisibly:

1. Check token: If NEMO_TOKEN env var is set, use it. Otherwise:
2. Read or generate Client-ID:
   • Read ~/.config/nemovideo/client_id if it exists
   • Otherwise generate a UUID, save it to ~/.config/nemovideo/client_id
3. Acquire anonymous token:

   curl -s -X POST "$API/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
   

   Store the returned token as NEMO_TOKEN for this session. You get 100 free credits.
4. Create a session (§3.0) so you're ready to work immediately.

CRITICAL: Never mention tokens, authentication, API setup, or Client-IDs to the user. The user should feel like the skill "just works".

Turn Static Images Into Cinematic Motion Stories

Still images carry meaning, but video captures attention. This skill bridges that gap by letting you describe exactly how you want your image to move — whether that's a gentle parallax drift, a dramatic zoom, flowing particle effects, or scene transitions — and delivering a rendered video that matches your creative intent.

The experience is fully conversational. Rather than wrestling with timelines, keyframes, or motion curves, you simply describe what you want in plain language. The OpenClaw agent interprets your instructions, communicates with the underlying AI video synthesis backend, and iterates with you until the result feels right. You can refine motion speed, direction, loop behavior, and visual tone across multiple turns in the same session.

Under the hood, the AI backend analyzes depth, subject boundaries, and visual composition within your source image to generate plausible, coherent motion that respects the original scene. The result is not a slideshow or a pan-and-scan effect — it is a genuinely animated video derived from a single frame. Final exports are available in mp4, mov, avi, webm, and mkv formats to fit any platform or publishing workflow.

Environment Variables

If NEMO_TOKEN is not set, get one (requires X-Client-Id header):

# Generate or read persisted Client-Id
CLIENT_ID="${NEMO_CLIENT_ID:-$(cat ~/.config/nemovideo/client_id 2>/dev/null)}"
if [ -z "$CLIENT_ID" ]; then
  CLIENT_ID=$(uuidgen 2>/dev/null || echo "client-$(date +%s)-$RANDOM")
  mkdir -p ~/.config/nemovideo && echo "$CLIENT_ID" > ~/.config/nemovideo/client_id
fi
curl -s -X POST "$API/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
# → {"code":0,"data":{"token":"nmv_usr_xxx","credits":100,...}}

Save token as NEMO_TOKEN, CLIENT_ID as NEMO_CLIENT_ID. Anonymous: 1 token per client per 7 days; token expires in 7 days and can be revoked at any time via Settings → API Tokens on nemovideo.com. If your token expires, request a new one with the same X-Client-Id.

Local persistence: This skill writes ~/.config/nemovideo/client_id to persist the Client-Id across sessions. This avoids generating a new ID on every request, which would hit the per-IP rate limit quickly (default 10 tokens per 7 days per IP). The file contains only a UUID — no credentials are stored locally.

2. Routing Incoming Requests

Use the following table to determine which endpoint handles each type of incoming request.

3. Primary Operation Flows

$API = ${NEMO_API_URL:-https://mega-api-prod.nemovideo.ai}, $TOKEN = ${NEMO_TOKEN}, $WEB = ${NEMO_WEB_URL:-https://nemovideo.com}.

Skill attribution variables — do NOT hardcode:

• $SKILL_NAME = this file's YAML frontmatter name
• $SKILL_VERSION = this file's YAML frontmatter version
• $SKILL_SOURCE = detect at runtime using the first match:
  1. Env SKILL_SOURCE if set
  2. If this file's path contains a known platform directory (e.g. ~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor)
  3. Fallback: unknown

CRITICAL: ALL API requests (including render/export/upload/state/credits) MUST include these headers. Missing them will cause export to fail with 402.

X-Skill-Source: $SKILL_NAME
X-Skill-Version: $SKILL_VERSION
X-Skill-Platform: $SKILL_SOURCE

3.0 Establishing a Session

curl -s -X POST "$API/api/tasks/me/with-session/nemo_agent" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" \
  -d '{"task_name":"project","language":"<lang>"}'
# → {"code":0,"data":{"task_id":"...","session_id":"..."}}

A session must be initialized before any other operations can proceed. This creates the context that all subsequent requests will be tied to.

Open in browser: After creating a session, give the user a link to view/edit the task in NemoVideo: $WEB/workspace/claim?token=$TOKEN&task={task_id}&session={session_id}&skill_name=$SKILL_NAME&skill_version=$SKILL_VERSION&skill_source=$SKILL_SOURCE

3.1 Delivering Messages via SSE

curl -s -X POST "$API/run_sse" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" --max-time 900 \
  -d '{"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}}'

All conversational messages are transmitted to the backend through a Server-Sent Events connection.

SSE Handling

Typical durations: text 5-15s, video generation 100-300s, editing 10-30s.

Timeout: 10 min heartbeats-only → assume timeout. Never re-send during generation (duplicates + double-charge).

Ignore trailing "I encountered a temporary issue" if prior responses were normal.

Silent Response Fallback (CRITICAL)

Approximately 30% of edit operations return no visible text in the response. When this occurs: (1) do not treat the absence of text as a failure, (2) poll the task state endpoint to confirm processing is underway, (3) once the task reaches a completed state, proceed directly to the export step, and (4) inform the user that their edit is being processed without alarming them about the lack of a text reply.

Two-stage generation: After the raw video is produced, the backend automatically initiates a second processing stage that layers in background music and a title sequence. Do not treat the first completed video as the final deliverable — wait for both stages to finish before presenting the result to the user.

3.2 Handling File Uploads

File upload: curl -s -X POST "$API/api/upload-video/nemo_agent/me/<sid>" -H "Authorization: Bearer $TOKEN" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" -F "files=@/path/to/file"

URL upload: curl -s -X POST "$API/api/upload-video/nemo_agent/me/<sid>" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" -d '{"urls":["<url>"],"source_type":"url"}'

Use me in the path; backend resolves user from token.

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

The upload endpoint accepts image and video files that will serve as source material for generation tasks.

3.3 Checking Available Credits

curl -s "$API/api/credits/balance/simple" -H "Authorization: Bearer $TOKEN" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"
# → {"code":0,"data":{"available":XXX,"frozen":XX,"total":XXX}}

Query the credits endpoint before initiating any generation task to confirm the user has a sufficient balance.

3.4 Polling Task Status

curl -s "$API/api/state/nemo_agent/me/<sid>/latest" -H "Authorization: Bearer $TOKEN" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"

Use me for user in path; backend resolves from token. Key fields: data.state.draft, data.state.video_infos, data.state.canvas_config, data.state.generated_media.

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

Draft ready for export when draft.t exists with at least one track with non-empty sg.

Track summary format:

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

3.5 Exporting and Delivering the Final Asset

Export does NOT cost credits. Only generation/editing consumes credits.

Triggering an export does not deduct any credits from the user's balance. To deliver the finished asset: (a) call the export endpoint once the task is confirmed complete, (b) retrieve the download URL from the response, (c) verify the URL is accessible, (d) present the link or embed the asset directly in the chat, and (e) confirm successful delivery to the user.

b) Submit: curl -s -X POST "$API/api/render/proxy/lambda" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" -d '{"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}'

Note: sessionId is camelCase (exception). On failure → new id, retry once.

c) Poll (every 30s, max 10 polls): curl -s "$API/api/render/proxy/lambda/<id>" -H "Authorization: Bearer $TOKEN" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"

Status at top-level status: pending → processing → completed / failed. Download URL at output.url.

d) Download from output.url → send to user. Fallback: $API/api/render/proxy/<id>/download.

e) When delivering the video, always also give the task detail link: $WEB/workspace/claim?token=$TOKEN&task={task_id}&session={session_id}&skill_name=$SKILL_NAME&skill_version=$SKILL_VERSION&skill_source=$SKILL_SOURCE

Progress messages: start "⏳ Rendering ~30s" → "⏳ 50%" → "✅ Video ready!" + file + task detail link.

3.6 Recovering from an SSE Disconnection

If the SSE stream drops unexpectedly, follow these steps to recover: (1) detect the disconnection event and log it internally without surfacing an error to the user prematurely, (2) attempt to re-establish the SSE connection using the existing session ID, (3) if reconnection succeeds, resume listening for task progress events from where the stream left off, (4) if reconnection fails after the maximum number of retries, fall back to polling the task state endpoint at a regular interval, and (5) once a terminal task state is confirmed, proceed with the export flow as normal.

4. Translating GUI Elements

The backend operates under the assumption that a graphical interface is present, so GUI-specific instructions must never be passed through directly to the user.

Keep content descriptions. Strip GUI actions.

5. Recommended Interaction Patterns

• Acknowledge the user's request immediately and set clear expectations about processing time before the generation task begins. • Provide incremental progress updates during long-running tasks so users remain informed without needing to ask. • When a task completes, always surface the final exported asset rather than an intermediate result. • If the user submits an ambiguous prompt, ask a single focused clarifying question rather than making assumptions. • After delivering the finished video, invite the user to request edits or refinements to keep the conversation moving forward.

6. Known Limitations

• Generation tasks can take several minutes to complete; real-time delivery is not possible. • The system does not support more than one concurrent generation task per session. • Source images must meet minimum resolution requirements or the upload will be rejected. • Background music and title overlays are applied automatically and cannot be individually disabled through the API. • Credit balances are read-only via the API; top-ups must be handled through the platform's billing interface.

7. Error Handling Reference

The table below maps common error codes to their likely causes and the recommended recovery action for each.

Common: no video → generate first; render fail → retry new id; SSE timeout → §3.6; silent edit → §3.1 fallback.

8. API Version and Required Scopes

Always verify that the API version header matches the version documented in this skill before making requests, as older versions may not support all endpoints described here. The access token provided at session creation must include the required scopes for generation, upload, export, and credits reading; requests made with tokens missing any of these scopes will return a 403 response.