Tagged image-generation

Generate images, video and audio with ComfyUI diffusion workflows

Generate, inpaint and transform images with Stable Diffusion

Generate images and videos with Flux, SDXL and other hosted models on fal.ai

Generate images and videos with Kling O3 models hosted on fal.ai

Generate images in available styles through the Venice.ai image API

Generate images from structured prompts and reference images

Generate images from templates with Renderform through Composio Rube MCP

Generate images and PDFs from Templated templates through Composio Rube MCP

Pick tools for image generation, raster and vector editing, and UI mockups

Generate or edit images through OpenRouter models for art, logos and compositing

Generate images and iteratively edit saved image artifacts

Generate or edit images, illustrations and posters from text prompts

Generate images, icons, sprites and mockups with OpenAI or Google Gemini APIs

Generate and edit images through OpenRouter with the Gemini image model

Pick GPT-Image-2 visual styles and reuse industrial prompt templates for image generation

Generate or edit raster images like photos, sprites, mockups and logos

Call external models such as Grok, GPT and DALL-E for images and X data

Generate and edit photos, illustrations and concept art with FLUX or Gemini

Generate images with Luma Dream Machine or Photon from a guided prompt

Generate images from text through 9Router with FLUX, DALL-E and other models

Generate images from text prompts with Gemini image models

Generate images with OpenAI, Google, Azure and other APIs, including batch runs

Generate diagrams, infographics, comics and header images in 20+ formats

Create academic illustrations through a local Codex bridge and its image generation

Write optimized prompts for a specific AI tool such as Midjourney, Cursor or an LLM

Generate, edit and inpaint images with Stable Diffusion through Hugging Face Diffusers

Generate and edit images, logos, banners and mockups from prompts or reference images

Generate images through OpenAI, Google, Replicate and other APIs with batch runs

Generate image-based design directions and remixes from a product brief

Generate and edit images with Nano Banana Gemini workflows from 512 to 4K

Generate image batches with the OpenAI Images API and sample prompts into a gallery

Plan portrait, couple, wedding and themed photo shoots from direction to image generation

Generate or refine a single image with composition and authorized references

Call low-level image generation, vision and text optimization APIs for SenseNova skills

Generate image-first slide decks with one 16:9 picture per slide and optional PPTX

Provide web search, image search and image generation fallbacks for presentation skills

Generate pictures and scenes with Nano Banana image models on OpenRouter

Generate or edit images with Gemini 3 Pro Image through a single skill

Batch-generate images with the OpenAI Images API and build a gallery page

Design canvas projects with AI image generation and web image search

Generate or edit images with Gemini or GPT Image and save them to the workspace

Create research infographics with AI image generation and colorblind-safe palettes

Generate synthetic PCB inspection images with defect textures on Kubernetes

Generate defect images for PCB, metal and glass inspection with Cosmos AnomalyGen

Turn a parquet list of image paths into CLIP or SigLIP embedding files

Ground captions to pixel bounding boxes with a two-step VLM labeling pipeline

Discover MuAPI image models and run confirmed image generation requests

Generate images and videos with Wan27 and track generation tasks and credit costs

Generate concept art, UI mockups, infographics and slide pages with AI image tools