Free Video Generator Hugging Face

Turn a text prompt describing a sunset over mountains into 720p AI generated video just by typing what you need. Whether it's generating short videos from te...

Security Scan

The skill's runtime instructions mostly match a cloud video-generation service, but the package name/description (mentions Hugging Face) doesn't match the actual API it calls (nemovideo.ai), and the instructions ask the agent to inspect local paths and persist session state — review these mismatches and the remote endpoint before installing.

Purpose & Capability

The skill claims to be a 'Free Video Generator Hugging Face' but the SKILL.md directs all traffic to https://mega-api-prod.nemovideo.ai and uses a NEMO_TOKEN for auth. Requesting a NEMO_TOKEN is coherent for a nemo API client, but the 'Hugging Face' label is misleading. Metadata also references a local config path (~/.config/nemovideo/), which suggests local config that isn't explained by the description.

Instruction Scope

Instructions are detailed and stay within video-generation workflows (create session, SSE conversation, upload, poll export). However the skill also instructs the agent to detect install path (~/.clawhub/, ~/.cursor/skills/) to set an X-Skill-Platform header and references a local config path; that requires reading the user's home filesystem. It also tells the agent to 'save session_id' (ambiguous where/how) — both are scope items users should be aware of but are not obviously malicious.

Install Mechanism

No install specification or code is provided (instruction-only). Nothing will be downloaded or written to disk by an installer step from the skill package itself.

Credentials

Only a single credential (NEMO_TOKEN) is required, and the SKILL.md provides an anonymous-token flow so a user secret is not strictly necessary. That is proportionate for a cloud API client. Minor concern: the metadata lists a config path (~/.config/nemovideo/), and the runtime asks to probe install paths in the home directory — this expands filesystem access beyond strictly sending user-provided files for upload.

Persistence & Privilege

The skill is not always-enabled and does not request elevated platform privileges. It does expect to persist or remember a session_id/token between calls (normal for a client talking to a remote API), but the SKILL.md is ambiguous about where session data is stored; this is a benign-but-notable implementation detail to confirm before use.

What to consider before installing

This skill appears to be an instruction-only client for the nemo video API (mega-api-prod.nemovideo.ai), not a direct Hugging Face integration despite its name. Before installing: 1) Decide whether you trust nemovideo.ai — the skill will send prompts, uploads, and may obtain an anonymous NEMO_TOKEN from that service. 2) Avoid uploading sensitive files (private videos, credentials). 3) Ask the skill author or registry for the source/homepage and privacy policy — there is none listed. 4) Confirm how/where session_id and tokens are stored (in-memory vs. written to disk) if you care about local persistence. 5) If you expected a pure Hugging Face workflow, look for a different skill or ask the maintainer to clarify the backend. If any of these mismatches are unacceptable, do not install.

Getting Started

Got text prompts or images to work with? Send it over and tell me what you need — I'll take care of the AI video generation.

Try saying:

• "generate a text prompt describing a sunset over mountains into a 720p MP4"
• "generate a 10-second video clip from my text description using a free Hugging Face model"
• "generating short videos from text prompts using free open-source models for developers and AI enthusiasts"

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.

Free Video Generator Hugging Face — Generate Videos From Text Prompts

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

Say you have a text prompt describing a sunset over mountains and want to generate a 10-second video clip from my text description using a free Hugging Face model — the backend processes it in about 1-3 minutes and hands you a 720p MP4.

Tip: shorter prompts with clear scene descriptions produce more consistent results.

Matching Input to Actions

User prompts referencing free video generator hugging face, 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.

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

• X-Skill-Source: free-video-generator-hugging-face
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

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

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.

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)

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

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a 10-second video clip from my text description using a free Hugging Face model" — concrete instructions get better results.

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

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "generate a 10-second video clip from my text description using a free Hugging Face model" → 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.