Generate images locally from prompts using Ollama models.
npx skills add https://github.com/SteveGJones/jack-tar-deckhand --skill ollama-image
Please help me install this Agent Skill. Skill: ollama-image Source: https://github.com/SteveGJones/jack-tar-deckhand/tree/main/plugins/jack-tar-ollama/skills/image Command: npx skills add https://github.com/SteveGJones/jack-tar-deckhand --skill ollama-image
Generating high-quality visuals locally from prompts, enabling offline workflows and keeping data on your machine.
Provide a prompt or prompt file to generate an image and save it to the desired output path.
High-intent search queries and answers about installing and using this skill.
You can generate images locally using Ollama models by providing a direct text prompt or a prompt file. The Skill renders the image without cloud calls and saves the output to a user-specified file path.
Yes, iterative refinement is supported through an optional review-and-refine loop. This uses vision-based evaluation to assess the generated image and automatically refine the prompt for subsequent local generation attempts.
Local image generation with Ollama operates entirely offline by keeping data on your machine. It uses Ollama integration to render images without making any external cloud calls, ensuring your data remains private.
The best way to provide complex prompts for local image generation is by using the prompt-file input option. This allows you to load detailed instructions from a file instead of passing a direct text prompt inline.
Yes, the Skill handles defaults for both model selection and image dimensions during Ollama image generation. You can generate images while relying on these built-in defaults or specify your desired output path.
Using local models for image generation enables completely offline workflows and keeps your prompt data on your machine. This approach eliminates cloud API dependencies and ensures privacy during the rendering process.
E01NExpose local Ollama models through an MCP server with two tools.
quanganh208Process media files for encoding, conversion, filtering, thumbnails, and AI background removal.
lukebazeDesign structured prompts for AI text and image generation models.
redfox-dataGenerate images from text prompts using the gpt-image-2 model.
