Make images with AI agents

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 .md to its path. Before generating anything, show the person the options on the use-case page.

Images for your video and around it: YouTube thumbnails, consistent characters and locations, style references, art styles, logos and brand kits.

Images & thumbnails (20)

Image models, YouTube thumbnails, covers, carousels, upscaling and background removal.

• Higgsfield YouTube Thumbnail — Workflow: Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
• Slack GIF Creator — Workflow: Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
• Baoyu Cover Image — Workflow: Article cover images built from five dimensions (type, palette, rendering, text, mood) in 2.35:1, 16:9 or 1:1.
• Anatomy Isometric Figures — Style: Detailed interactive isometric SVG figures that explain a technical idea as a physical object, with optional WebGL.

Step by step: YouTube thumbnails and covers, TikTok / Instagram photo carousels

Characters (4)

Consistent characters across shots: face IDs, character sheets and casting.

• Higgsfield Soul ID — Model: Train a reusable face model from your photos for identity-consistent images and video on Higgsfield.
• fal Character Design — Prompt: Design original characters that stay consistent: reference and expression sheets, outfits, character-to-video.
• Character Design Sheet — Prompt: Keep a character consistent across AI images with turnarounds, expression sheets, palettes and LoRAs.
• Consistent Characters — Workflow: Multi-scene ads where the same actors, outfits and location hold in every cut: cards, composites, Kling v3 clips.

Step by step: Same character in every scene, Exercise demo loops, Put your character into a reference video

Scenes & locations (0)

Places and sets that stay the same across shots: interiors, landscapes, location sheets.

Style references (3)

Mood boards and references from film stills, Pinterest and Are.na, turned into prompts.

• GPT Image 2 Style Library — Style: Pick styles and industrial prompt templates for GPT Image 2/2.5 from a 530+ case library (a 35K-star repo).
• FrameThrower Film References — Style: Film stills from 5,489 films, searchable by lighting, lens, shot size, color and mood.
• Are.na MCP — Style: Build and read Are.na moodboard channels from your agent.

Art styles (6)

ASCII, collage, pixel art, watercolor, oil paint, p5 and generative looks.

• Canvas Design — Style: Design posters and visual art as PNG or PDF from a written design philosophy, with 54 bundled fonts.
• Algorithmic Art — Style: Create original generative art in p5.js: write an algorithmic philosophy, then code it with seeded randomness.
• Lemo-Opuscar Film Styles — Style: 59 film styles made entirely in code (oil paint, watercolor, ukiyo-e, satellite briefing, exploded teardown).
• fal Game Dev — Style: Generate 2D pixel-art game assets: characters, sprite sheets, walk and attack cycles, parallax backgrounds.

Logos & brand kits (3)

Logo design, brand kits and guidelines: marks, palettes, type.

• Brand Guidelines — Style: Apply Anthropic's colors and typography to any artifact; a compact template for your own brand skill.
• Higgsfield Brandkit — Workflow: Build a complete visual identity: palette, SVG logo marks, type, mockups, packaging and an editable brandbook.
• Logo Design Guide — Guide: Design logos with AI image models: logo types, prompting techniques, scalability rules and iteration.