Living Editorial Banner — trending format for images & thumbnails
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the use-case page.
A split 16:9 card: a static serif headline and stats beside an AI painting that breathes with subtle motion.
- Slug:
want-living-editorial-banner - Status: wanted
- Publisher: ben (Contra Labs) (community)
- Source: https://x.com/contraben/status/2074943936570024126
- Cost: ~60–85 credits / banner (estimate) — One hero image (GPT Image 2.5 at 2.1–23.1 or Nano Banana 2.1 at 5.25–15.75) + a 5 s Kling v3 pass at 11.8 credits/s (~59), catalog of 2026-10-23.
What it does
A research or brand-comms card: the left panel is static typography (logo, serif headline, reviewer avatars) and the right is an AI "oil painting" with minimal motion (locked camera, light flicker, micro-movement), which makes a stat feel like an editorial cover. The sample's own thread was a blind test showing the image model should follow the brief. An agent routes the hero image by brief (Muse for graphic looks, GPT Image 2.5 or Nano Banana 2.1 for painterly ones), animates it with a gentle image-to-video pass, keeps every word in HTML so text never warps, and exports 16:9, 1:1 and 4:5.
Status
A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.
Example: https://x.com/contraben/status/2074943936570024126
How an agent would make it: Headline + stat → hero image routed by brief → subtle image-to-video with a locked camera → HTML split layout → 16:9, 1:1 and 4:5 exports
Models it drives: muse_image, gpt_image_2_5, nano_banana_2_1, kling_v3
Example output
https://skills.varg.ai/previews/want-living-editorial-banner.mp4 — Contra Labs research card: static serif headline, logo and reviewer avatars on the left, an AI 'oil painting' (made with Meta Muse Image) with a glowing laptop and slight light flicker on the right (first 8 s of 16 s) (credit: ben (@contraben), Contra Labs, https://x.com/contraben/status/2074943936570024126)
More images & thumbnails skills
- Higgsfield YouTube Thumbnail: Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
- Slack GIF Creator: Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
- PixiJS GIFs: Load, play and control animated GIFs inside a PixiJS v8 scene.
- AI Image Generation: Generate images with 50+ models from one CLI: GPT Image 2.5, FLUX, Gemini, Grok, Seedream, Reve and more.
- Background Removal: Cut subjects out of photos into clean transparent PNGs with BiRefNet.
- FLUX Image: Generate and restyle images with FLUX Dev LoRA and FLUX.2 Klein, including custom LoRA styles.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt