Image To Video In Filmora

Turn five product photos in JPG format into 1080p animated video clips just by typing what you need. Whether it's converting photo collections into shareable...

Security Scan

The skill's network calls and token usage generally match a video-rendering service, but there are inconsistent metadata/config-reading instructions and a few unclear behaviors (filesystem probing, hidden technical details) that do not clearly match the declared requirements.

Purpose & Capability

The skill claims to convert images to videos and only requests a single NEMO_TOKEN credential — that aligns with calling a remote rendering API. However the SKILL.md frontmatter and instructions reference a config path (~/.config/nemovideo/) and reading install path indicators (~/.clawhub/, ~/.cursor/skills/) even though the registry metadata lists no required config paths. That mismatch is unexplained and notable.

Instruction Scope

Runtime instructions direct the agent to call the nemovideo API endpoints (session creation, SSE, upload, render) which is consistent. Concerns: (1) the skill tells the agent to read this file's YAML frontmatter and to detect install paths in the user's home directory — filesystem probing outside the immediate task may reveal other environment details; (2) it instructs the agent to 'Keep the technical details out of the chat', which encourages non-transparent background activity; (3) the skill also instructs generating and using anonymous tokens automatically if NEMO_TOKEN is absent, which causes outbound requests and creation of credentials without explicit user action.

Install Mechanism

No install spec or code files — instruction-only. This minimizes on-disk risk because nothing is downloaded or executed by the skill itself.

Credentials

The declared main credential (NEMO_TOKEN) is reasonable for a remote rendering service. However the SKILL.md also references a config directory (~/.config/nemovideo/) and requires reading install paths to set X-Skill-Platform — neither is declared in the registry metadata, creating an unexplained request to access filesystem-config data. Automatic anonymous-token acquisition is allowed by the instructions, which means the agent will obtain and use credentials on the user's behalf if NEMO_TOKEN is missing.

Persistence & Privilege

The skill is not always-enabled and does not request elevated privileges. Autonomous invocation is allowed (platform default). The only persistence-like behavior documented is that session tokens and render job IDs are used server-side; there is no instruction to modify other skills or system-wide settings.

What to consider before installing

This skill appears to implement a legitimate image→video API workflow, but there are a few red flags you should consider before enabling it: - Verify the NEMO_TOKEN source and trustworthiness of the 'mega-api-prod.nemovideo.ai' service. The token gives the skill API access to upload your images and request renders. If you don't trust the endpoint, do not provide credentials or allow uploads. - Ask the publisher (or reject) to explain why the skill needs to read ~/.config/nemovideo/ and probe install paths (~/.clawhub/, ~/.cursor/skills/). These filesystem accesses are not documented in the registry metadata and may reveal more of your environment than necessary. - Be aware that the skill will automatically obtain an anonymous token if NEMO_TOKEN is not present (it will POST to the external API). If you prefer explicit consent for credential creation or outbound network calls, do not install or require the skill to ask first. - Avoid uploading sensitive images to any third-party rendering service unless you are comfortable with their privacy policy. Consider testing with non-sensitive images first or running in an isolated environment. If the publisher can clarify the config-path/read-access rationale and remove the instruction to hide technical details from users, this would reduce the concerns.

Getting Started

Ready when you are. Drop your still images here or describe what you want to make.

Try saying:

• "convert five product photos in JPG format into a 1080p MP4"
• "turn my images into a slideshow video with transitions and music"
• "converting photo collections into shareable videos for social media creators"

Getting Connected

Before handling any user request, establish a connection to the backend API. Show a brief status like "Connecting...".

If NEMO_TOKEN is in the environment, use it directly and create a session. Otherwise, acquire a free starter token:

• Generate a UUID as client identifier
• POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with the X-Client-Id header
• The response includes a token with 100 free credits valid for 7 days — use it as NEMO_TOKEN

Then create a session by POSTing to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer authorization and body {"task_name":"project","language":"en"}. The session_id in the response is needed for all following requests.

Tell the user you're ready. Keep the technical details out of the chat.

Image to Video in Filmora — Convert Photos into Shareable Videos

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 five product photos in JPG format, type "turn my images into a slideshow video with transitions and music", and you'll get a 1080p MP4 back in roughly 1-2 minutes. All rendering happens server-side.

Worth noting: using fewer than 10 images keeps the output tight and under a minute long.

Matching Input to Actions

User prompts referencing image to video in filmora, 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.

Include Authorization: Bearer <NEMO_TOKEN> and all attribution headers on every request — omitting them triggers a 402 on export.

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

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

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 my images into a slideshow video with transitions and music" — 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 platforms like YouTube and Instagram.

Common Workflows

Quick edit: Upload → "turn my images into a slideshow video with transitions and music" → Download MP4. Takes 1-2 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.