# Images & thumbnails: agent skills for AI images and YouTube thumbnails

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page.

Image models, YouTube thumbnails, covers, carousels, upscaling and background removal. 50 skills for Claude Code, Codex and Grok, by type: workflows take a brief to a finished video, effects and styles change how it looks, prompts and guides teach the agent the craft, models run the generation.

## How-to tutorials

- [How to make YouTube video thumbnails with AI](https://varg.ai/how-to/make-youtube-video-thumbnails.md): High-CTR thumbnails and vertical covers, in a few options to choose from.
- [How to make TikTok photo carousels with AI](https://varg.ai/how-to/make-tiktok-photo-carousels.md): Swipeable photo slideshows with hook text — the format app founders use for organic growth.

## Skills (50)

### Prompts (4)

- [Replicate Prompt Images](https://varg.ai/how-to/skills/replicate-prompt-images.md) — Replicate: Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.
- [FLUX Image Best Practices](https://varg.ai/how-to/skills/flux-image-best-practices.md) — Black Forest Labs: Prompt FLUX image models well: structure, JSON prompts, hex colors, typography and multi-reference edits.
- [Douyin Cover Builder](https://varg.ai/how-to/skills/douyin-cover-builder.md) — 0x00000003, beta: Writes image-model prompts for Douyin covers: bold title, highlighted keywords, your face bottom right
- [Composition & Framing](https://varg.ai/how-to/skills/craft-composition-framing.md) — varg, beta: 34 composition cards — thirds, symmetry, leading lines, forced perspective, 2.39:1 to IMAX — for stills and video.

### Styles (3)

- [Canvas Design](https://varg.ai/how-to/skills/anthropic-canvas-design.md) — Anthropic: Design posters and visual art as PNG or PDF from a written design philosophy, with 54 bundled fonts.
- [GPT Image 2 Style Library](https://varg.ai/how-to/skills/gpt-image-2-style-library.md) — Canghe: Pick styles and industrial prompt templates for GPT Image 2/2.5 from a 530+ case library (a 35K-star repo).
- [Anatomy Isometric Figures](https://varg.ai/how-to/skills/anatomy-isometric.md) — Ryan: Detailed interactive isometric SVG figures that explain a technical idea as a physical object, with optional WebGL.

### Guides (8)

- [HyperFrames Media Use](https://varg.ai/how-to/skills/hyperframes-media-use.md) — HeyGen: Find or make every asset a video needs: music, SFX, voiceover, images, logos, avatars, transcripts, grades.
- [PixiJS GIFs](https://varg.ai/how-to/skills/pixijs-gif.md) — PixiJS: Load, play and control animated GIFs inside a PixiJS v8 scene.
- [App Store Screenshots](https://varg.ai/how-to/skills/inference-sh-app-store-screenshots.md) — inference.sh: Make App Store and Google Play screenshots to exact specs: sizes, gallery order, mockups and previews.
- [Book Cover Design](https://varg.ai/how-to/skills/inference-sh-book-cover-design.md) — inference.sh: Design book covers that fit their genre: typography rules, sizing, thumbnail tests and AI iterations.
- [Logo Design Guide](https://varg.ai/how-to/skills/inference-sh-logo-design-guide.md) — inference.sh: Design logos with AI image models: logo types, prompting techniques, scalability rules and iteration.
- [OG Image Design](https://varg.ai/how-to/skills/inference-sh-og-image-design.md) — inference.sh: Design Open Graph and social share images to platform specs, with text placement and branding.
- [YouTube Thumbnail Design](https://varg.ai/how-to/skills/inference-sh-youtube-thumbnail-design.md) — inference.sh: Design YouTube thumbnails that read on a phone: dimensions, contrast, safe zones, text and faces.
- [Social Media Carousel](https://varg.ai/how-to/skills/inference-sh-social-media-carousel.md) — inference.sh: Design swipeable carousels for Instagram, LinkedIn and X: slide structure, hooks, text hierarchy.

### Workflows (6)

- [Higgsfield Brandkit](https://varg.ai/how-to/skills/higgsfield-brandkit.md) — Higgsfield: Build a complete visual identity: palette, SVG logo marks, type, mockups, packaging and an editable brandbook.
- [Higgsfield YouTube Thumbnail](https://varg.ai/how-to/skills/higgsfield-youtube-thumbnail.md) — Higgsfield: Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
- [Slack GIF Creator](https://varg.ai/how-to/skills/anthropic-slack-gif-creator.md) — Anthropic: Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
- [ASO App Store Screenshots](https://varg.ai/how-to/skills/aso-appstore-screenshots.md) — Adam Lyttle: App Store screenshots from your codebase: finds the core benefits, pairs simulator shots, then composes and enhances.
- [E-commerce Image Studio](https://varg.ai/how-to/skills/ecom-image2.md) — buluslan: 39 e-commerce image templates (main images, lifestyle, A+, sizes, GIFs) with one style lock across a campaign set.
- [Baoyu Cover Image](https://varg.ai/how-to/skills/baoyu-cover-image.md) — Jim Liu: Article cover images built from five dimensions (type, palette, rendering, text, mood) in 2.35:1, 16:9 or 1:1.

### Models & tools (29)

- [varg AI](https://varg.ai/how-to/skills/varg-ai.md) — varg: The official varg skill: videos, images, speech and music through one API key, rendered in the cloud or locally.
- [Higgsfield Generate](https://varg.ai/how-to/skills/higgsfield-generate.md) — Higgsfield: Generate images, video, 3D and audio across 30+ models, plus ad videos and virality scoring, from one CLI.
- [fal Models Catalog](https://varg.ai/how-to/skills/fal-models-catalog.md) — fal: Choose the right fal endpoint for any modality from curated picks: image, video, 3D, audio and vision.
- [fal genmedia](https://varg.ai/how-to/skills/fal-genmedia.md) — fal: Run any of 1,200+ fal endpoints from the terminal: search, inspect schema, price, run, poll and download.
- [fal Model Routing](https://varg.ai/how-to/skills/fal-model-routing.md) — fal: Pick default fal endpoints per job: premium stills, fast drafts, edits, video, lip-sync and campaign work.
- [Gemini API Dev](https://varg.ai/how-to/skills/gemini-api-dev.md) — Google Gemini: Write current Gemini API code, including Nano Banana image generation, Omni video and Gemini TTS.
- [Melies](https://varg.ai/how-to/skills/melies.md) — Melies: Generate images, video, movie posters and thumbnails from the terminal with 148 AI actors and style flags.
- [AI Image Generation](https://varg.ai/how-to/skills/inference-sh-ai-image-generation.md) — inference.sh: Generate images with 50+ models from one CLI: GPT Image 2.5, FLUX, Gemini, Grok, Seedream, Reve and more.
- [Background Removal](https://varg.ai/how-to/skills/inference-sh-background-removal.md) — inference.sh: Cut subjects out of photos into clean transparent PNGs with BiRefNet.
- [FLUX Image](https://varg.ai/how-to/skills/inference-sh-flux-image.md) — inference.sh: Generate and restyle images with FLUX Dev LoRA and FLUX.2 Klein, including custom LoRA styles.
- [GPT Image](https://varg.ai/how-to/skills/inference-sh-gpt-image.md) — inference.sh: Generate and edit images with OpenAI GPT Image 2.5 and GPT Image 2 from the command line.
- [Image Upscaling](https://varg.ai/how-to/skills/inference-sh-image-upscaling.md) — inference.sh: Upscale and enhance low-resolution images with Real-ESRGAN, Thera, Topaz or the FLUX upscaler.
- [Nano Banana](https://varg.ai/how-to/skills/inference-sh-nano-banana.md) — inference.sh: Generate and edit images with Google's Gemini 3 Pro Image and Gemini 2.5 Flash Image, multi-image input too.
- [Nano Banana 2](https://varg.ai/how-to/skills/inference-sh-nano-banana-2.md) — inference.sh: Generate and edit images with Nano Banana 2, with up to 14 reference images and search grounding.
- [P-Image](https://varg.ai/how-to/skills/inference-sh-p-image.md) — inference.sh: Generate and edit images fast with Pruna's P-Image models, including LoRA styles and multi-image edits.
- [Qwen Image 2](https://varg.ai/how-to/skills/inference-sh-qwen-image-2.md) — inference.sh: Generate and edit images with Alibaba Qwen-Image 2.0: the fast model, or Pro for cleaner text rendering.
- [Qwen Image 2 Pro](https://varg.ai/how-to/skills/inference-sh-qwen-image-2-pro.md) — inference.sh: Make posters, banners and text-heavy designs with Qwen-Image 2.0 Pro's precise text rendering.
- [inference.sh CLI](https://varg.ai/how-to/skills/infsh-cli.md) — inference.sh: Log in to inference.sh and run its catalog of AI apps — image, video, audio, LLMs, search — from one CLI.
- [Runway Dev](https://varg.ai/how-to/skills/runway-dev.md) — Runway: Build Runway's image, video and audio models into your app: live API contracts, SDK and server-side keys.
- [Runway Model Routers](https://varg.ai/how-to/skills/runway-dev-model-routers.md) — Runway: Send generation through a saved Runway Model Router config instead of hard-coding one model.
- [Runway Dev Models](https://varg.ai/how-to/skills/runway-dev-models.md) — Runway: Add a direct Runway model endpoint to your app for image, video or audio, following the live contract.
- [Runway Recipes](https://varg.ai/how-to/skills/runway-dev-recipes.md) — Runway: Integrate Runway's prebuilt multi-step image and video Recipes using the live Recipe guide.
- [Runway Media](https://varg.ai/how-to/skills/runway-media.md) — Runway: Generate and edit images, video, music, speech and sound effects from chat with Runway's MCP tools.
- [Runway Studio Skills](https://varg.ai/how-to/skills/runway-studio-skills.md) — Runway: Run Runway's API from Python scripts: text, image and video-to-video, character performance, images, TTS.
- [BFL API](https://varg.ai/how-to/skills/bfl-api.md) — Black Forest Labs: Integrate the FLUX API correctly: endpoints, async polling, webhooks, rate limits, errors and regions.
- [Krea Generate](https://varg.ai/how-to/skills/krea-generate.md) — Krea: Pick the right Krea model and prompt for any image, video, edit or upscale before you generate.
- [Kling AI](https://varg.ai/how-to/skills/klingai.md) — Kling AI, beta: Official Kling CLI: text/image-to-video, Omni reference and edit, images, reusable subjects, quota
- [dLazy Jimeng Text-to-Image](https://varg.ai/how-to/skills/dlazy-jimeng-t2i.md) — dlazyai, beta: Generates images with Jimeng (Dreamina) from a prompt and up to 10 reference images, through the dLazy CLI
- [dLazy Kling Image O1](https://varg.ai/how-to/skills/dlazy-kling-image-o1.md) — dlazyai, beta: Kling o1 text-to-image and reference-image editing at 2K via the dLazy CLI