Generate images from text prompts via OpenAI or Stable Diffusion endpoints.
npx skills add https://github.com/47network/Sven --skill image-generation-47network
Please help me install this Agent Skill. Skill: image-generation Source: https://github.com/47network/Sven/tree/main/skills/image-generation Command: npx skills add https://github.com/47network/Sven --skill image-generation-47network
Generating high-quality visuals from simple text prompts eliminates manual design work and speeds up concept creation.
Provide a text prompt and optional provider, size, number of images, and style to generate visuals.
High-intent search queries and answers about installing and using this skill.
Image generation from text prompts works by sending your descriptive text to either the OpenAI image generation API or a Stable Diffusion endpoint. It applies optional size, style, and quantity parameters to output readily renderable visuals for design or marketing workflows.
You need an OPENAI_API_KEY to generate AI images using OpenAI endpoints. Alternatively, you can configure a STABLE_DIFFUSION_URL to route text prompts through a Stable Diffusion endpoint instead.
You can generate multiple AI images with custom sizes in one request. The generation process accepts optional style modifiers, image count, and size parameters to fit your specific creative and prototyping workflows.
Visual content generation via Stable Diffusion endpoints works by sending text prompts to a configured STABLE_DIFFUSION_URL. It validates inputs and handles errors gracefully while applying optional style parameters to produce images.
AI image generation validates prompt inputs and handles API errors gracefully. This ensures automation workflows for creating visual content remain stable even if OpenAI or Stable Diffusion endpoints encounter issues.
moltis-orgTranscribe audio files via OpenAI's Whisper API endpoint.
modu-aiEmbed "AI 생성" labels in image and video metadata with visual watermarks.
QuestNova502Generate images and text via the Gemini Web backend with batch prompts.
LocalKinAIGenerate images from prompts via a local OllamaDiffuser API server.
