Muse Image 1.0: Image Edit
Edit an image with precision using Muse Image 1.0, following natural language instructions to alter specific elements while preserving the rest of the scene. Takes 2 input images and produces 1 edited output image. Ideal for product photography touch-ups, creative style transfers, and iterative visual refinement.
About
This workflow uses Muse Image 1.0 to edit an image with natural-language instructions while preserving the rest of the scene. Two LoadImage nodes supply inputs: one is the primary image you want to edit, and the second is a visual reference that guides the look (style, color palette, material cues) of the edit. The MetaMuseImageEditApi node sends both images plus your instruction to the hosted Muse Image 1.0 service and returns a single edited image. SaveImageAdvanced then writes the result to disk with your chosen filename and subfolder.
What you provide
- Reading the workflow
Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.
Try in CloudQuestions & answers
The first (primary) image is the one being edited. The second is a visual reference to guide the edit’s style, palette, or material cues. If you don’t want external guidance, you can use the same image for both inputs.
Yes. MetaMuseImageEditApi calls a hosted Muse Image 1.0 service. Ensure your endpoint and credentials are set in the node or ComfyUI’s API settings before running the workflow.
Be explicit and constraint-focused: name the object and change ("Make the door matte black"), and add preservation cues ("keep walls, lighting, and background unchanged"). Using a closely matched reference image further improves locality and style consistency.
Increase instruction specificity (e.g., "leave background untouched"), choose a closer-matching reference image, and iterate. Small phrasing adjustments often reduce unintended global changes.