[GH-ISSUE #1] Fantastic control, but blurry results #3

Open
opened 2026-10-30 21:03:55 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @frostyfrolics on GitHub (Apr 10, 2025).
Original GitHub issue: https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/1

I have been using the canny model and it is working great to replicate a pose. However, the results are pretty grainy/fuzzy.
But, they are great first pass to get a pose, and they clean up pretty well when taken to img2img to process again with the same prompt.
Thank you for this.

Originally created by @frostyfrolics on GitHub (Apr 10, 2025). Original GitHub issue: https://github.com/AcademiaSD/sd-forge-fluxtools-v2/issues/1 I have been using the canny model and it is working great to replicate a pose. However, the results are pretty grainy/fuzzy. But, they are great first pass to get a pose, and they clean up pretty well when taken to img2img to process again with the same prompt. Thank you for this.
Author
Owner

@AcademiaSD commented on GitHub (Apr 10, 2025):

You can get better results directly by increasing the number of steps, lowering the Strength and End of the tool.

<!-- gh-comment-id:2791946975 --> @AcademiaSD commented on GitHub (Apr 10, 2025): You can get better results directly by increasing the number of steps, lowering the Strength and End of the tool.
Sign in to join this conversation.
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
AcademiaSD/sd-forge-fluxtools-v2#3
No description provided.