Hi @glass cargo. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
#Edit canny and reuse?
gleaming kayakBOT
To create a Canny guide, you would typically use the Canny model in the Text to Image Adapter (T2I-Adapter) as described in the Invoke AI support article (https://support.invoke.ai/support/solutions/articles/151000165024-using-text-to-image-adapter-t2i-adapter-). The Canny model works by detecting the edges in an image by looking for abrupt changes in intensity.
Once you have generated the image, you can save it and then edit it as needed. After editing, you can use the edited image as a new Canny guide.
However, if you're seeing double lines, it might be due to the way the Canny model works. It's known for its ability to detect edges accurately while reducing noise and false edges. If the double lines are not desired, you might need to adjust the thresholds or use a different model.
If you're seeing two images from every iteration, one of them is the final generated image, and the other is an intermediate image. You can clear the intermediate image by going to settings and selecting "Clear Intermediates" as mentioned in this Github issue (https://github.com/invoke-ai/InvokeAI/issues/4719).