Image Photo Generator

generate text prompts into AI generated images with this skill. Works with JPG, PNG, WEBP, SVG files up to 200MB. marketers, content creators, designers use...

Security Scan

This skill is internally consistent with its stated purpose (generating images via the NemoVideo backend) but it will contact a third‑party service, create/store a short‑lived token, and may read a local config/install path — you should only install it if you trust that remote service and are comfortable with uploading files to it.

Purpose & Capability

Name/description match the runtime instructions: the SKILL.md documents calls to a NemoVideo API and requires a NEMO_TOKEN. Requiring a token and describing upload, SSE, render and export workflows is appropriate for an image-generation backend.

Instruction Scope

Instructions include steps to obtain an anonymous token, create sessions, stream SSE messages, upload files (multipart or URL), poll renders, and translate GUI actions to API calls. These actions are coherent with the skill's purpose. The doc also tells the agent to detect install path (~/.clawhub/, ~/.cursor/skills/) to set a header and to read a config path (~/.config/nemovideo/) per frontmatter metadata — these require accessing the local filesystem, which is reasonable for attribution but broader than purely stateless API usage and should be noted.

Install Mechanism

Instruction-only skill with no install spec or code files. No packages or external installers are fetched by the skill itself, which minimizes on-disk risk.

Credentials

The skill only declares a single credential (NEMO_TOKEN), which is appropriate. However the SKILL.md metadata also references a config path (~/.config/nemovideo/) and instructs detecting install paths — these imply the skill may read local files/config for attribution or persisted tokens. Registry metadata earlier indicated no required configPaths, which is inconsistent with the SKILL.md frontmatter.

Persistence & Privilege

always:false and normal autonomous invocation are used. Skill asks to store session_id and may store the anonymous token for the session lifetime; it does not request persistent elevated privileges or modify other skills. This level of persistence is typical for a service client.

Assessment

What to consider before installing: - Trust the remote service: the skill will call https://mega-api-prod.nemovideo.ai, upload files you provide, and obtain/store a short-lived anonymous token (100 free credits, valid ~7 days). Only use it if you trust that endpoint and its data handling/retention policies. - Token storage: the SKILL.md instructs obtaining/storing a NEMO_TOKEN if none is present. Ask or check where the token/session_id are persisted (memory vs filesystem vs ~/.config/nemovideo/) and how to revoke/delete them. - Local file access: the skill may read install paths and a config directory for attribution and may upload files referenced by path. Do not supply sensitive local files or secrets in prompts/uploads. - Metadata discrepancy: the registry listing said no config paths, but the SKILL.md frontmatter references ~/.config/nemovideo/ — this mismatch is likely an authoring oversight but worth clarifying. - Privacy & retention: confirm the vendor's policy for uploaded media (retention, sharing, indexing). Uploaded content is sent to a third party. - If you need higher assurance: request the skill author to clarify where tokens are stored, confirm whether the skill writes to disk, and provide a privacy/retention statement from the backend service.

Getting Started

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

Try saying:

• "generate my text prompts"
• "export 1080p MP4"
• "generate a realistic photo of a"

First-Time Connection

When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").

Authentication: Check if NEMO_TOKEN is set in the environment. If it is, skip to step 2.

1. Obtain a free token: Generate a random UUID as client identifier. POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id set to that UUID. The response data.token is your NEMO_TOKEN — 100 free credits, valid 7 days.
2. Create a session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Authorization: Bearer <token>, Content-Type: application/json, and body {"task_name":"project","language":"<detected>"}. Store the returned session_id for all subsequent requests.

Keep setup communication brief. Don't display raw API responses or token values to the user.

Image Photo Generator — Generate Photos from Text Prompts

Send me your text prompts and describe the result you want. The AI image generation runs on remote GPU nodes — nothing to install on your machine.

A quick example: upload a short text description like 'sunset over mountain lake', type "generate a realistic photo of a city street at night with rain reflections", and you'll get a 1080p MP4 back in roughly 20-40 seconds. All rendering happens server-side.

Worth noting: more specific prompts produce more accurate and usable images.

Matching Input to Actions

User prompts referencing image photo generator, 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: image-photo-generator
• 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

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 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)

Common Workflows

Quick edit: Upload → "generate a realistic photo of a city street at night with rain reflections" → Download MP4. Takes 20-40 seconds 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.

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "generate a realistic photo of a city street at night with rain reflections" — concrete instructions get better results.

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

Export as PNG for transparent backgrounds or JPG for smaller file sizes.