Videoagent Image Studio
Generate still images for video-agent workflows through a single script that polls providers and returns a unified success/imageUrl payload.
Overview
Videoagent Image Studio is an agent skill for the Build phase that generates images via fal.ai and Legnext-backed models with one-shot script execution and a unified JSON result object.
Install
npx skills add https://github.com/pexoai/pexo-skills --skill videoagent-image-studioWhat is this skill?
- v2.0.0 simplified SKILL.md: run script once—internal polling, no manual async/poll steps
- Unified result shape: success, model, imageUrl, images, jobId across providers
- Model table covers Flux, SDXL, Nano Banana, Ideogram, Recraft (fal.ai) and Midjourney (Legnext)
- Optional hosted or self-hosted proxy with IMAGE_STUDIO_PROXY_URL and pro keys
- Env-driven FAL_KEY, LEGNEXT_KEY, and VALID_PRO_KEYS for self-hosted access control
- v2.0.0 release (2026-03-03)
- Unified 5-field output shape: success, model, imageUrl, images, jobId
Adoption & trust: 5.4k installs on skills.sh; 732 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your video agent needs images from several providers but async job polling and inconsistent response shapes slow automation.
Who is it for?
Builders composing Pexo-style video agents who want multi-model image generation with env-based keys and optional self-hosted proxy control.
Skip if: Teams that only need a single manual image in a design tool, or workflows with no API budget and no willingness to manage FAL_KEY/LEGNEXT_KEY secrets.
When should I use this skill?
User or video-agent workflow needs generated still images from configured fal.ai or Legnext models via the image studio script or proxy.
What do I get? / Deliverables
You run one command path and receive a consistent { success, model, imageUrl, images, jobId } payload ready for the next video-agent step.
- Generated image URL(s)
- Structured job result with model and jobId
Recommended Skills
Journey fit
How it compares
Scripted multi-provider image generator for agents—not a browser-only design skill or a general MCP catalog entry.
Common Questions / FAQ
Who is videoagent-image-studio for?
Solo builders and small teams wiring automated video or creative agents that must fetch stills from Flux, SDXL, Ideogram, Recraft, Nano Banana, or Midjourney-backed APIs.
When should I use videoagent-image-studio?
Use it in Build while assembling agent-tooling for generative pipelines—storyboards, scene stills, or promo frames—when you want one run-and-wait flow instead of a 3-step async poll recipe.
Is videoagent-image-studio safe to install?
It expects API keys and optional proxy auth; review the Security Audits panel on this page and never commit FAL_KEY, LEGNEXT_KEY, or VALID_PRO_KEYS into a public repo.
SKILL.md
READMESKILL.md - Videoagent Image Studio
# ── Client-side (optional) ────────────────────────────────────────────────── # Custom proxy URL — leave empty to use the default hosted proxy # IMAGE_STUDIO_PROXY_URL=https://your-proxy.vercel.app/api/image # Pro access key for custom proxy authentication # IMAGE_STUDIO_API_KEY=your_pro_key_here # ── Server-side (only needed if self-hosting the proxy) ───────────────────── # fal.ai API Key — required for Flux, SDXL, Nano Banana, Ideogram, Recraft # Get it at: https://fal.ai/dashboard/keys # FAL_KEY=your_fal_key_here # Legnext.ai API Key — required for Midjourney # Get it at: https://legnext.ai/dashboard # LEGNEXT_KEY=your_legnext_key_here # Comma-separated list of valid pro keys for access control (leave empty for open access) # VALID_PRO_KEYS=key1,key2,key3 # Changelog All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). ## [2.0.0] - 2026-03-03 ### Changed - **Simplified SKILL.md**: Removed the complex 3-step async/poll workflow from the main instructions. The script already handles all polling internally — the SKILL.md now reflects this with a single, clean "run and get result" pattern. - **Unified output format**: All models now return a consistent `{ success, model, imageUrl, images, jobId }` shape, making it easier to handle results uniformly. - **Clearer model selection table**: Added "Speed" column so agents can make better trade-off decisions. - **Added "Use when" trigger**: SKILL.md now starts with a clear activation condition so the agent knows exactly when to invoke this skill. - **Documented `--reference-images` for Nano Banana**: Pass comma-separated URLs for character/style consistency across sequential image generations. --- ## [1.3.0] - 2026-02-25 ### Added - **Non-blocking async mode for Midjourney** (`--async` flag). Submit a job and return immediately with `job_id`, without waiting for completion. This prevents the bot from being blocked while waiting for image generation. - **Status poll mode** (`--poll --job-id <id>`). Check job status once and return immediately — no waiting. Returns `status: "completed"`, `"pending"`, `"processing"`, or `"failed"`. - Updated SKILL.md with mandatory async workflow documentation. All Midjourney requests should now use `--async` + periodic `--poll` to avoid blocking the bot. ### Changed - `--async` flag is supported for all Midjourney actions: `imagine`, `upscale`, `variation`, `reroll`. --- ## [1.2.0] - 2026-02-25 ### Changed - **Midjourney Turbo mode enabled by default.** The `--turbo` flag is now automatically appended to all Midjourney prompts, reducing generation time from ~30-60s to ~10-20s (requires Midjourney Pro or Mega subscription). - Added `--mode` parameter: `turbo` (default), `fast`, `relax`. --- ## [1.1.0] - 2026-02-25 ### Changed - **Midjourney provider switched from TTAPI to Legnext.ai** for faster generation speed and higher stability. - Environment variable renamed from `TTAPI_KEY` to `LEGNEXT_KEY`. Please update your OpenClaw config. - Upscale now supports `--upscale-type` parameter: `0` = Subtle (default), `1` = Creative. - Variation now supports `--variation-type` parameter: `0` = Subtle (default), `1` = Strong. - Added `--action reroll` support for Midjourney. - Added `--action describe` support for Midjourney. - Response now includes `imageUrls` array (4 individual image URLs) in addition to the grid `imageUrl`. ### Migration Guide If you were using `TTAPI_KEY`, please: 1. Register at [legnext.ai](https://legnext.ai) and get your API key. 2. Update `~/.openclaw/openclaw.json`: rename `TTAPI_KEY` to `LEGNEXT_KEY` and set your new key. --- ## [1.0.0] - 2026-02-25 ### Added - Initial release of the unified image generation skill. - **Midjourney** support via TTAPI (imagine, upscale U1-U4, variation V1-V4, reroll, zoom, pan). - **Flux 1.1 Pro** su