Image To Video Lora

Turn a single portrait photo or product image into 1080p animated video clips just by typing what you need. Whether it's turning still images into short anim...

Security Scan

The skill's behavior mostly matches its stated purpose (cloud-based image→video via a Nemo API) but there are inconsistencies and a few operational details you should verify before installing or using it.

Purpose & Capability

The skill's name/description align with the runtime instructions: it calls a remote Nemo video render API, uploads images, and retrieves MP4s. However, the skill frontmatter in SKILL.md declares a required config path (~/.config/nemovideo/) while the registry metadata lists no required config paths — this discrepancy is unexplained and could indicate the skill expects to read local configuration files that were not declared in the registry entry.

Instruction Scope

SKILL.md contains concrete API calls and an explicit workflow (auth, create session, upload, SSE chat, export) limited to the Nemo backend. It does not instruct reading arbitrary system files or other unrelated credentials. It does, however, instruct the agent to obtain an anonymous token automatically if no NEMO_TOKEN is present (calls an external auth endpoint), which means the agent will contact an external service even when you haven't provided credentials.

Install Mechanism

This is instruction-only with no install spec and no code files, so nothing will be downloaded or written by an installer. That lowers the risk surface.

Credentials

The only declared credential is NEMO_TOKEN (primary), which is proportional for a cloud API service. The SKILL.md also specifies an optional anonymous-token flow when NEMO_TOKEN is absent. The inconsistency about the config path in the SKILL.md frontmatter means the skill may try to access ~/.config/nemovideo/ for additional credentials or state — this was not listed in the registry metadata and should be clarified.

Persistence & Privilege

always:false and no install steps are present. The skill does not request persistent system-wide privileges. It creates sessions with the remote backend but does not request to modify other skills or global agent settings.

What to consider before installing

This skill appears to do what it claims (upload images to a cloud render API and return videos), but check two things before installing or using it: (1) confirm whether it actually needs to read ~/.config/nemovideo/ (the SKILL.md frontmatter declares that config path but the registry entry did not) — if it does, inspect that directory to see what will be exposed; (2) understand that if you don't supply NEMO_TOKEN the agent will automatically request an anonymous token from https://mega-api-prod.nemovideo.ai, so your images and data will be uploaded to that third-party service regardless. Also verify the provenance of NEMO_TOKEN and the Nemo service (privacy, retention, and cost/credits), and avoid providing other unrelated credentials. If the registry owner can confirm and correct the config-path discrepancy and provide a privacy/terms URL for the backend, my confidence would increase.

Getting Started

Send me your images and I'll handle the LoRA video generation. Or just describe what you're after.

Try saying:

• "convert a single portrait photo or product image into a 1080p MP4"
• "animate this photo into a 5-second video using a cinematic LoRA style"
• "turning still images into short animated videos using custom LoRA models for AI artists and content 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 LoRA — Animate images with LoRA styles

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

Here's a typical use: you send a a single portrait photo or product image, ask for animate this photo into a 5-second video using a cinematic LoRA style, and about 1-3 minutes later you've got a MP4 file ready to download. The whole thing runs at 1080p by default.

One thing worth knowing — high-contrast images with clear subjects produce the most consistent motion results.

Matching Input to Actions

User prompts referencing image to video lora, 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.

All calls go to https://mega-api-prod.nemovideo.ai. The main endpoints:

1. Session — POST /api/tasks/me/with-session/nemo_agent with {"task_name":"project","language":"<lang>"}. Gives you a session_id.
2. Chat (SSE) — POST /run_sse with session_id and your message in new_message.parts[0].text. Set Accept: text/event-stream. Up to 15 min.
3. Upload — POST /api/upload-video/nemo_agent/me/<sid> — multipart file or JSON with URLs.
4. Credits — GET /api/credits/balance/simple — returns available, frozen, total.
5. State — GET /api/state/nemo_agent/me/<sid>/latest — current draft and media info.
6. Export — POST /api/render/proxy/lambda with render ID and draft JSON. Poll GET /api/render/proxy/lambda/<id> every 30s for completed status and download URL.

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

Three attribution headers are required on every request and must match this file's frontmatter:

Header	Value
X-Skill-Source	image-to-video-lora
X-Skill-Version	frontmatter version
X-Skill-Platform	auto-detect: clawhub / cursor / unknown from install path

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.

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)

Backend Response Translation

The backend assumes a GUI exists. Translate these into API actions:

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"	Query session state
"drag/drop" / "拖拽"	Send edit via SSE
"preview in timeline"	Show track summary
"Export button" / "导出"	Execute 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.

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "animate this photo into a 5-second video using a cinematic LoRA style" — concrete instructions get better results.

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

PNG images preserve detail better than JPG when used as LoRA animation inputs.

Common Workflows

Quick edit: Upload → "animate this photo into a 5-second video using a cinematic LoRA style" → Download MP4. Takes 1-3 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.