AI_SDXL_inpainting_with_GroundedSAM2 - 100-hours-a-week/16-Hot6-wiki GitHub Wiki
μμ λ¬Έμλ‘ μ΄λ : AI Wiki
- The SDXL Inpainting model edits or fills parts of an image based on a mask and a text prompt.
-
Origin Image
-
Mask Image
We used Grounded SAM2 for masking to precisely define the areas for SDXL Inpainting. Grouded with SAM2
1 | 2 | 3 |
---|---|---|
![]() |
![]() |
![]() |
- These images were generated using different prompts to explore various outputs.
- The mask images are a bit jagged, which results in less clean inpainting outputs.
- Imprecise masking of the 'desk' and 'deskmat' appears to cause issues in the final output.
- Generate a mask image that excludes the desk and deskmat from the inpainting area.