“Image generation”

Generate dynamic social preview images using Next.js file conventions and the next/og library.

Generate images with Venice.

Make an image from a description with FLUX.2 klein on moria's GPU, about 20 seconds, and attach it.

调用 nano banana API（gemini-3.1-flash-image-preview）生成图片。支持纯文本生图和参考图生图。

Generate images with Maxfusion.

Generates images from text prompts using MuAPI.

Turns a product photo or URL into a static image ad — one image, or a set.

當使用者要求生成圖片、海報、封面、角色視覺或場景示意圖時使用。先收斂成單張圖片 prompt，再呼叫 generate_image 工具實際產圖，避免只描述而沒有真的生成。

Generate images via Stable Diffusion (HuggingFace Diffusers, local/API)

Use the local imgen CLI whenever the user asks to "generate an image", create an image, edit an image, inspect an image, or produce a raster asset.

Generate images using Stable Diffusion via HuggingFace Diffusers library locally or via API

Generate or edit images using AI models (FLUX, Gemini).

Generate images from text prompts using Google Gemini

Best quality AI image generation (~$0.12-0.20/image).

Generates illustrations and photos with an AI image provider (Gemini or OpenAI) after the person approves the cost, and marks every result as AI-generated.

Skill for routing approved image-generation requests through the generator specialist and generic FAL tools.

Generate a new image or edit existing images and return the result to the chat.

Generate a unique Open Graph image for every page so link previews on social platforms and chat apps render correctly.

Generate high-quality images from text prompts using Hugging Face FLUX primary and Prexzy backup.

使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。

Supports text-to-image and image-to-image.

Generate 2K images using Gemini 3 Pro API.

Generate professional visuals using Gemini via browser automation with 6-gate quality control.

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image).