Hugging Face Free Video Generation

Turn a short text description like 'a fox running through a snowy forest' into 720p AI generated clips just by typing what you need. Whether it's generating...

Security Scan

The skill's instructions broadly match a cloud video-rendering integration, but its name/branding (Hugging Face) does not match the actual API domain (nemovideo.ai), and the runtime instructions ask the agent to read installation paths and set platform headers not fully declared — these mismatches merit caution.

Purpose & Capability

The skill is named and marketed as 'Hugging Face Free Video Generation' but all runtime endpoints and tokens reference nemovideo.ai / NEMO_TOKEN rather than Hugging Face APIs or credentials. This branding/API mismatch is unexpected and could be misleading. Aside from the name, the required NEMO_TOKEN and the API endpoints are coherent for a NemoVideo-like service, but the Hugging Face label is inconsistent with the actual required credentials and endpoints.

Instruction Scope

The SKILL.md instructs the agent to perform network calls (anonymous-token, session creation, SSE, uploads, renders) and to persist a session_id. Those actions are coherent for a cloud render pipeline. However the instructions also direct the agent to detect its install path to set X-Skill-Platform (checking for ~/.clawhub/, ~/.cursor/skills/), which implies reading agent/host filesystem locations that were not declared in the skill's required configPaths. That filesystem probing is outside what the description implies and is a scope mismatch. The doc also instructs generating and exchanging anonymous tokens automatically, which is expected but worth noting since it results in outbound requests to an external API.

Install Mechanism

This is an instruction-only skill with no install spec and no code files. That minimizes on-disk execution risk; nothing is downloaded or extracted by the skill itself.

Credentials

The skill only requires a single env var (NEMO_TOKEN), which aligns with the API it calls. However, the required credential name and declared config path (~/.config/nemovideo/) are inconsistent with the advertised 'Hugging Face' branding, which would normally require Hugging Face credentials. The single-token model is proportionate for the described API usage, but the naming/branding mismatch is suspicious and should be clarified.

Persistence & Privilege

The skill does not request always: true and does not declare system-wide modifications. It instructs saving session_id and using tokens for API calls, which is normal for a session-based cloud service. There is no explicit instruction to modify other skills or global agent settings.

What to consider before installing

This skill looks like a wrapper for a NemoVideo API but is labeled 'Hugging Face', which is inconsistent and could be misleading. Before installing or using it, confirm: (1) why the Hugging Face name is used when the endpoints are on mega-api-prod.nemovideo.ai; (2) whether you trust sending media and possibly sensitive prompts to that external service; (3) whether you are comfortable setting/providing a NEMO_TOKEN or allowing the skill to generate anonymous tokens and upload files. Also ask the author to document exactly what is stored and where (session IDs, uploaded media), and to remove any filesystem probing that isn't necessary (the SKILL.md's install-path detection). If you cannot verify the skill's origin or developer, avoid providing real credentials or sensitive content.

Getting Started

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

Try saying:

• "generate my text prompts"
• "export 720p MP4"
• "generate a 5-second video clip of"

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.

Hugging Face Free Video Generation — Generate AI Videos From Text

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

Say you have a short text description like 'a fox running through a snowy forest' and want to generate a 5-second video clip of a sunset over the ocean with calm waves — the backend processes it in about 1-3 minutes and hands you a 720p MP4.

Tip: shorter prompts with clear subjects produce more consistent results.

Matching Input to Actions

User prompts referencing hugging face free video generation, 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 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.

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

• X-Skill-Source: hugging-face-free-video-generation
• 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 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

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

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.

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 "generate a 5-second video clip of a sunset over the ocean with calm waves" — concrete instructions get better results.

Max file size is 200MB. Stick to MP4, GIF, WebM, PNG for the smoothest experience.

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "generate a 5-second video clip of a sunset over the ocean with calm waves" → 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.