Getting Started

Session: POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Keep the returned session_id for all operations.

Let the user know with a brief "Ready!" when setup is complete. Don't expose tokens or raw API output.

Turn Still Photos Into Living, Breathing Video Clips

There's a specific kind of magic in watching a frozen moment suddenly move — a portrait where the wind shifts through someone's hair, a landscape where clouds begin to drift, a product shot that subtly pulses with life. This skill makes that possible through a simple two-step process: upload your image and describe what you want to see happen.

The prompt is where your creative control lives. You can be poetic ('golden hour light sweeps across the field as birds take flight') or direct ('camera slowly zooms in, subject turns head slightly'). The AI interprets your intent and generates a short video clip that matches the visual style of your original photo while adding the motion you described.

This tool is built for people who want professional-looking animated content without learning complex motion graphics software. Social media creators, small business owners, bloggers, and digital artists all find real value here — turning product photos into engaging ads, portraits into memorable reels, or concept art into animated previews. It's free to use online, with no installation required.

Routing Your Animation Requests

When you submit an image alongside your motion prompt, the skill parses your input and routes the animation job to the appropriate AI video generation pipeline based on clip length, style parameters, and available processing capacity.

Cloud Rendering API Reference

Frames are diffused server-side using a latent video diffusion model, meaning your source image and text prompt are encoded into a noise-guided temporal sequence before being decoded into smooth, rendered output frames. All rendering happens in the cloud — no local GPU required — so even complex motion prompts with camera pan or subject animation finish without taxing your device.

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

• X-Skill-Source: image-to-video-ai-with-prompt-online-free
• 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.

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

~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.

Backend Response Translation

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

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)

Error Handling

Frequently Asked Questions

Do I need to sign up or pay to use this? No — this is an image-to-video-ai-with-prompt-online-free tool, meaning you can generate animated video clips from your images at no cost, directly in your browser.

What kinds of images work best? Clear, well-lit photos with a defined subject tend to produce the most coherent animations. Portrait photos, product shots, and landscape images all perform well. Very cluttered or low-resolution images may produce less precise motion.

How specific should my prompt be? More specific prompts generally yield better results. Instead of 'make it move,' try 'slow camera push-in with light flickering from the left.' That said, even simple prompts like 'gentle wind effect' work reliably.

How long are the generated videos? Output clips are typically 3–6 seconds, optimized for social media formats like Reels, Shorts, and Stories.

Performance Notes

Generation time depends on image resolution and prompt complexity. Most clips are ready within 15–45 seconds. Highly detailed prompts requesting multiple simultaneous motion elements may take slightly longer to process.

Prompt interpretation works best when you describe physical motion or lighting changes rather than abstract emotions. 'Warm golden light sweeps from right to left' will outperform 'make it feel nostalgic' in terms of visual accuracy.

Output quality is optimized for 1080p social media use. If you're working with a very high-resolution source image, the AI will preserve sharpness in the output while adding smooth motion without artifacts.

Edge cases to know: Images with highly transparent backgrounds or extreme contrast ratios may produce motion blur at subject edges. For best results, use images with natural backgrounds or clean, solid-color backdrops when precision matters.