edit-with-comfyui

Orchestrate Flux and Qwen-based prompts to edit images in ComfyUI.

3|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/erosDiffusion/ComfyUI-Erosdiffusion-LTX2 --skill edit-with-comfyui
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edit-with-comfyui
Source: https://github.com/erosDiffusion/ComfyUI-Erosdiffusion-LTX2/tree/main/.agent/skills/edit-with-comfyui
Command: npx skills add https://github.com/erosDiffusion/ComfyUI-Erosdiffusion-LTX2 --skill edit-with-comfyui

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Allows users to edit existing images within ComfyUI by leveraging Qwen 2.5VL, enabling prompt-driven modifications and optional camera adjustments.

Core Features & Use Cases

  • Prompt-based edits: Transform objects, adjust backgrounds, or apply stylistic changes using Qwen 2.5VL.
  • Camera changes: Support for zoom, angle shifts, and framing adjustments within edits.
  • Image analysis support: Optional analysis steps to inform edits and improve results.

Quick Start

Provide a source image path and an edit prompt; the system will apply the Flux Edit workflow to generate the edited image(s).

Frequently Asked Questions about edit-with-comfyui

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I edit images in ComfyUI using prompt-based instructions?

To edit images in ComfyUI using prompts, provide a source image path and an edit instruction. The system orchestrates Flux and Qwen 2.5VL to apply transformations like object changes or background adjustments.

Can I adjust camera angles in ComfyUI when modifying an existing image?

Yes, you can adjust camera angles in ComfyUI during image edits. The workflow supports camera changes like zoom, angle shifts, and framing adjustments directly through prompt instructions.

Does Qwen 2.5VL work with Flux for background changes in image editing workflows?

Qwen 2.5VL works with Flux to execute background changes in image editing workflows. Qwen handles the prompt-driven analysis and instructions while Flux applies the visual modifications.

What is the best way to transform objects in an image using ComfyUI workflows?

The best way to transform objects in ComfyUI is using a prompt-driven workflow. By supplying a source image and targeting the object with Qwen 2.5VL, you achieve precise object transformation.

Do I need image analysis steps to improve prompt-based edits in ComfyUI?

Image analysis steps are optional but recommended to improve prompt-based edits in ComfyUI. Analyzing the source image informs the Qwen and Flux workflow, yielding more accurate modifications.

Why use Qwen for image editing instead of standard ComfyUI nodes?

Using Qwen for image editing provides smart prompt orchestration that standard ComfyUI nodes lack. Qwen 2.5VL analyzes image references to guide Flux edits, enabling complex transformations and camera adjustments.