convez.ai
SkillDesign & UIIntermediário
Bria-AI

Bria AI Skills — Geração e Edição de Imagens Controlada

Bria-AI/bria-skill

Controle fino de geração e edição de imagens para agentes de código

Ver no GitHub
BomPluginScore · de 0 a 100

Conjunto de skills para Claude Code e 37+ agentes que oferece geração, edição e transformação de imagens com controle fino via modelos comercialmente seguros do Bria.ai. Inclui remoção de fundo (RMBG-2.0), edição por objeto, controle de iluminação/estilo/estação, upscaling e fotografia de produtos — tudo através de prompts estruturados (VGL) ou linguagem natural.

Instalação

$npx convez-ai Bria-AI/bria-skill

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
75
Forks
7
Acompanhando
1
Saúde
25%
Último commit
há 4 semanas
Versão
v1.7.0
Issues abertas
1
Contribuidores
3

Casos de uso

  • Gerar imagens de alta qualidade a partir de prompts com controle estruturado
  • Editar objetos específicos em imagens (substituir, adicionar, remover por nome)
  • Remover fundos automaticamente e gerar cutouts limpos
  • Aplicar transformações independentes (iluminação, estilo, estação) sem alterar conteúdo
  • Criar assets de fotografia de produtos com cenários controlados

Veredito

Skill robusta e bem integrada que democratiza controle fino em geração de imagens para agentes de código. A combinação de VGL estruturado + edição por objeto + remoção de fundo resolve casos reais de design e conteúdo visual sem exigir expertise em prompt engineering. Requer API key do Bria.ai, mas instalação é trivial.

README

A tradução para o português deste README ainda está na fila.

Bria AI Skills — Controllable Image Generation for Coding Agents

Generate, edit, and precisely control images directly from your AI coding agent using Bria.ai's commercially-safe models. Unlike black-box generators, Bria gives you fine-grained control: edit specific objects, mask regions, control lighting/season/style independently, and chain operations in pipelines.

Works with: Claude Code, Cursor, Cline, Codex, and 37+ other agents

Quick Start

1. Install

Claude Code (plugin): add the marketplace, then install the plugin:

/plugin marketplace add Bria-AI/bria-skill
/plugin install bria-ai@bria-skills

The marketplace also bundles the remove-background, vgl, and image-utils plugins — install any of them the same way (e.g. /plugin install remove-background@bria-skills).

Other agents (Cursor, Cline, Codex, and 37+ more):

npx skills add bria-ai/bria-skill

2. Get a free API key

Sign up at platform.bria.ai and create an API key.

3. Set the key

export BRIA_API_KEY="your-key-here"

Or just start using the skill — it will walk you through setup automatically.

4. Use it

Ask your agent to generate images, remove backgrounds, edit photos, and more. The skill handles the rest.

Skills Included

SkillDescription
bria-aiControllable image generation & editing — 18+ capabilities including text-to-image, object-level editing, background removal, upscaling, restyling, relighting, and product photography
remove-backgroundDedicated background removal — transparent PNGs, cutouts, and foreground extraction powered by RMBG 2.0. Fastest path for background removal tasks
vglMaximum generation control — structured JSON (Visual Generation Language) that explicitly defines objects, lighting, camera, composition, and style for deterministic, reproducible results
image-utilsClassic image manipulation — resize, crop, composite, watermarks, format conversion with Python Pillow

What You Can Control

CapabilityControl LevelExample
Generate images from textPrompt + aspect ratio + VGL structured JSON"A modern office with natural lighting, 16:9"
Edit specific objectsObject-level — add, replace, or remove by name"Replace the red mug with a blue one"
Edit by instructionImage-level — natural language control"Change the mug color to red"
Edit masked regionsPixel-level — paint exactly where to changeInpaint only the sky, leave everything else
Remove backgroundsAutomatic — clean transparent PNGsOne API call, no manual masking
Control lightingIndependent — change light without touching contentGolden hour, spotlight, dramatic shadows
Control styleIndependent — restyle without changing structureOil painting, anime, cartoon, 3D render
Control seasonIndependent — change season/weather onlySpring blossoms, winter snow
Expand imagesDirectional — extend boundaries with contextOutpaint to 16:9 from a square
Product photographyScene control — place products in any setting"Modern kitchen countertop, morning light"
Upscale resolution2x or 4x — preserves detailsSuper resolution enhancement
Pipeline chainingMulti-step — compose operations in sequenceGenerate -> remove BG -> lifestyle shot

Example Use Cases

Building a website? Ask: "Generate a hero image for a SaaS landing page, 16:9, modern and clean"

E-commerce catalog? Ask: "Remove the background from this product photo and place it in a kitchen scene"

Batch assets? Ask: "Generate product photos for these 5 items and create transparent PNGs for each"

Presentations? Ask: "Create a slide visual showing data analytics, blue gradient, corporate style"

Alternative Installation

Claude Code (direct)

claude mcp add bria-skills -- npx -y bria-skills

Cursor

Download the skill folders to ~/.cursor/skills/. Each skill is a folder containing a SKILL.md file.

Manual (any agent)

Copy the skills/ directory contents to your agent's skills directory.

Requirements

  • Bria API key — Free at platform.bria.ai
  • For image-utils: pip install Pillow requests

Documentation

License

MIT

Ver o original no GitHub

Bom para

Relacionados