AI Agent Skill: Generate Reference Images with ComfyUI

Product Description

The AI Agent Skill: Generate Reference Images with ComfyUI provides a structured approach for developers and teams to create character reference images, scene visuals, and keyframes for videos using ComfyUI in either a local or self-hosted remote environment. This capability does not include model weights or fixed character workflows, emphasizing the importance of a modular design.

What this skill does

• Clarifies the intended purpose by recording character features, fixed costumes, art styles, scene settings, composition, dimensions, and distinguishes between identity reference images and keyframes.
• Connects either to a default local instance or a user-specified remote server of ComfyUI.
• Matches model families and search criteria using SDXL and Anima-based models through Civitai or Hugging Face, ensuring required dependencies are accounted for.
• Prepares images by utilizing authorized workflows or templated processes, verifying all nodes, models, edges, sizes, prompts, seeds, and output nodes.
• Validates a single image initially before proceeding with batch processing, ensuring the image meets the stated requirements.
• Executes batch processing within budget constraints and manages failed items separately, providing documented image details, parameters, and acceptance conclusions.

Who it is for

This skill is suitable for developers and teams utilizing AI coding agents such as Claude Code, Cursor, and Codex who require a dependable solution for generating and managing visual reference materials.

Use cases

• Creating reference images for character design and development.
• Generating scene layouts for pre-visualization in film or animation projects.
• Producing keyframes for video content as part of a storyboard or animation sequence.

Technical details

• Requires access to ComfyUI, supporting both local and remote deployment configurations.
• Utilizes tools and integration with agent-skills, aiapplication, and comfyui-reference-images.
• Operates with model families and prompts from platforms like Civitai and Hugging Face for accurate model matching.
• Employs batch preparation and task recovery techniques as detailed in relevant documentation.
• Ensures compatibility with diverse execution environments and workflows.

Source & Licence

This package is built on open-source work published by Shenrui-Ma (Shenrui-Ma/video-regen-recipes) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.