Felldude/Moss Image Text Enhancement & Image to Text Node (Comfy Local)

Moss Image Text Enhancement Image to Text Node If an image is attached you can ask the LLM to describe the image, or describe in a style. Without an image attached you can ask for a long form prompt of x After the download is complete the node is 100% offline and reuses the text embedding as for the DiT so the model is very fast Place this .py file in your "custom_nodes" folder in comfy (Do not make a subfolder) The node can also be attached to text output allowing for synthetic training images to be generated with text caption matched Example: write a long form prompt describing a fantasy ima

<iframe src="https://silytics.si/embed/item/fd1b3bcb-e354-46df-ba97-cee52bdbccc3" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 30 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.