Image To Video Ltx

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

Security Scan

The skill's requirements and runtime instructions are consistent with an image→video cloud-rendering service: it only needs a single service token and calls a named backend API to upload images and start renders.

Purpose & Capability

Name/description match the behavior in SKILL.md. Requiring a NEMO_TOKEN and calling a nemo-video backend is coherent for an image→video rendering service.

Instruction Scope

Runtime instructions are limited to authenticating (using NEMO_TOKEN or acquiring an anonymous token), creating a session, uploading media, streaming SSE responses, polling render status, and returning download URLs. The skill asks the agent to read its own frontmatter and to detect the install path to set X-Skill-Platform — this requires local file/metadata access but is reasonable for attribution. No instructions request unrelated system files, credentials, or broad data collection.

Install Mechanism

Instruction-only skill (no install spec, no code files). Lowest-risk install posture — nothing will be written to disk by an installer step.

Credentials

Only one credential (NEMO_TOKEN) is required and is the primary credential for the backend. The skill will generate an anonymous token from the service if NEMO_TOKEN is absent. Metadata declares a config path (~/.config/nemovideo/) which is not explicitly used in the runtime steps — this is a small metadata inconsistency but not a dangerous mismatch.

Persistence & Privilege

The skill is not always-enabled and does not request persistent platform privileges. It stores session_id for ongoing renders (expected for queued jobs) and does not instruct modifying other skills or system-wide settings.

Assessment

This skill behaves like a normal cloud-rendering integration: it will call https://mega-api-prod.nemovideo.ai to obtain anonymous tokens (if you don't supply NEMO_TOKEN), create sessions, upload your images/audio, and return a downloadable MP4. Before installing: (1) Be comfortable that you will upload media to that external service — avoid sending sensitive/private images. (2) If you prefer control, provide your own NEMO_TOKEN rather than letting the skill obtain an anonymous token. (3) Note the skill may read its own file frontmatter and detect install paths for attribution headers; this is normal but means the agent will access small local metadata. (4) The metadata lists a config path (~/.config/nemovideo/) that the instructions don’t otherwise use — if you are concerned about any local config access, ask the skill author to clarify why that path is declared. Overall the skill appears internally coherent for its stated purpose.

Getting Started

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

Try saying:

• "convert my still images"
• "export 1080p MP4"
• "animate 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 LTX — Convert Images into Video Clips

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

Here's a typical use: you send a a single product photo or landscape image, ask for animate this image into a 5-second video clip with smooth motion, and about 30-90 seconds later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — clean, high-contrast images with clear subjects produce smoother motion output.

Matching Input to Actions

User prompts referencing image to video ltx, 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.

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

Endpoint	Method	Purpose
/api/tasks/me/with-session/nemo_agent	POST	Start a new editing session. Body: {"task_name":"project","language":"<lang>"}. Returns session_id.
/run_sse	POST	Send 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>	POST	Upload a file (multipart) or URL.
/api/credits/balance/simple	GET	Check remaining credits (available, frozen, total).
/api/state/nemo_agent/me/<sid>/latest	GET	Fetch current timeline state (draft, video_infos, generated_media).
/api/render/proxy/lambda	POST	Start 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.

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

• X-Skill-Source: image-to-video-ltx
• 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.

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

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)

Tips and Tricks

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

Max file size is 20MB. Stick to JPG, PNG, WEBP, BMP for the smoothest experience.

Use PNG for best image quality input to preserve detail in the generated video.

Common Workflows

Quick edit: Upload → "animate this image into a 5-second 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.